# Fullstack Software Engineer (x/f/m) - Ops AI Platform
**Company:** [Alan](https://scaleengineer.com/companies/alan)
Join Alan's Ops AI Platform team as a Full Stack Software Engineer to build the future of work by creating AI agents that autonomously handle operational tasks at scale. This is a ground-zero opportunity to design and implement state-of-the-art systems integrating Large Language Models, tool calling, and human-in-the-loop workflows for internal operations. With 3+ years of product engineering experience and a strong systems architecture background, you'll influence platform architecture, mentor engineers, and see your work deployed in production immediately.
**Role:** Full Stack Engineer
**Seniority:** Mid
**Locations:** Anywhere in France, Belgium, Spain
**Salary:** 65000–95000 EUR
[Apply](https://jobs.ashbyhq.com/alan/e5daaf2e-a7fc-4823-bf6f-de056e137c44)
Canonical: https://scaleengineer.com/jobs/alan/fullstack-software-engineer-x-f-m-ops-ai-platform-e5daaf2e
---
## Responsibilities

- Implement AI Agent Capabilities and Tooling: Design and implement new capabilities for autonomous AI agents including tool calling, prompt management, multi-agent architectures, and context-aware interactions. Build comprehensive tooling that empowers non-technical operations team members to create, test, deploy, and monitor agents without requiring deep engineering expertise.
- Architect and Scale Ops AI Platform: Develop robust system architecture supporting scale from dozens to tens of thousands of automated tasks daily. Design scalable backend infrastructure handling LLM integrations, state management, and reliable task execution. Establish architectural patterns that enable progressive rollout, fine-grained permissions, and safe AI agent operations in production environments.
- Build Internal Tools UX for Agent Management: Create intuitive user interfaces enabling operators to monitor agents, review reasoning and action logs, provide follow-up instructions, and manage operational workflows. Design context-aware chat modals and dashboards that integrate AI agents as first-class citizens within existing internal tool ecosystems.
- Ensure Safety, Accuracy, and Reliability: Implement comprehensive testing frameworks, stateful evaluation systems, and robust validation mechanisms. Build human-in-the-loop workflows for sensitive actions, establish fine-grained permission systems, and create monitoring infrastructure ensuring AI agents operate safely and accurately in high-stakes operational contexts.
- Establish Integration with Internal and External Systems: Design and implement connections to internal business data systems, external APIs, and web dashboards without native APIs. Create flexible tool abstractions enabling agents to interact reliably with diverse technical interfaces and data sources across the organization.
- Mentor Engineers and Build Team Culture: Provide technical mentorship to engineering team members, contribute to establishing product and engineering culture standards, and participate actively in hiring and onboarding processes. Share knowledge on AI systems, full-stack architecture, and operational excellence with the growing team.

## Requirements

### education

- {"name":"Bachelor's Degree in Computer Science or Related Field","description":"Formal education in Computer Science, Software Engineering, or equivalent field providing strong foundations in algorithms, data structures, and computer systems. Or equivalent professional experience demonstrating mastery of core computer science concepts."}
- {"name":"Demonstrated Self-Directed Learning in AI/ML","description":"Evidence of continuous learning regarding AI, LLMs, machine learning frameworks, and agentic systems. This could be through online courses, personal projects, conference attendance, technical blog posts, or open-source contributions demonstrating deep engagement with emerging AI technologies."}

### technical

- {"name":"Full-Stack Software Engineering","description":"Demonstrated expertise building complete software systems from backend services to frontend user interfaces. Strong proficiency in modern backend frameworks, RESTful API design, database optimization, and full-stack system architecture. Experience with production-grade code quality and scalable systems."}
- {"name":"Systems Architecture and Backend Engineering","description":"Proven ability designing large-scale distributed systems with focus on reliability, performance, and maintainability. Deep understanding of system design principles, database strategies, caching layers, and infrastructure considerations. Strong spike in backend engineering with experience handling operational complexity and scaling challenges."}
- {"name":"Large Language Models and LLM Application Development","description":"Hands-on experience building applications with modern LLMs including prompt engineering, function calling, chain-of-thought patterns, and prompt optimization. Understanding of LLM limitations, hallucination mitigation, context management, and production deployment patterns. Experience with LLM frameworks and evaluation strategies."}
- {"name":"AI Agent Architecture and Multi-Agent Systems","description":"Experience designing and implementing autonomous agent systems, tool calling mechanisms, state management for agents, and multi-agent coordination patterns. Understanding of agentic workflows, decision trees, and reliable agent behaviors in complex operational contexts."}
- {"name":"Product Engineering Mindset","description":"Strong focus on building solutions that deliver measurable impact to end users. Ability to balance technical excellence with pragmatic delivery timelines. Experience shipping features that users genuinely adopt and finding value in. Comfortable making trade-off decisions based on user impact."}

### experience

- {"name":"3+ Years Product Engineering Experience","description":"Minimum three years building production software systems, with demonstrated progression in scope and impact. Experience owning features from conception through deployment and adoption. Track record of delivering technical solutions that solve real business problems for users."}
- {"name":"ML or MLOps Project Exposure","description":"Prior experience working with machine learning systems, ML model deployment, ML infrastructure, or ML operations. This could include training models, managing ML pipelines, monitoring model performance in production, or integrating ML capabilities into products. Understanding of ML-specific operational challenges is valuable."}
- {"name":"Internal Tools or Platform Engineering","description":"Experience building internal tools, platforms, or infrastructure serving engineering or operations teams. Understanding of the unique UX and reliability requirements when building tools used by internal users who depend on systems daily. Familiarity with rapid iteration and close user feedback loops."}
- {"name":"Scaling Systems at Production Scale","description":"Hands-on experience taking systems from prototype to production, scaling through 10x or greater growth in usage. Experience identifying and resolving bottlenecks, optimizing database queries, managing infrastructure costs, and maintaining reliability under increasing load."}

## Skills

### required

- {"name":"Python","description":"Production-grade Python expertise for backend services, API development, and AI system implementation. Strong understanding of Python best practices, async programming, testing frameworks, and performance optimization."}
- {"name":"Backend Framework (FastAPI, Django, or Flask)","description":"Deep experience building robust REST APIs and backend services using modern Python frameworks. Comfortable with request handling, middleware, validation, authentication, and API design patterns."}
- {"name":"TypeScript/JavaScript","description":"Strong TypeScript and JavaScript skills for frontend development, internal tools UX, and full-stack development. Experience with modern async patterns, DOM manipulation, and building responsive user interfaces."}
- {"name":"React or Modern Frontend Framework","description":"Proficiency building interactive user interfaces with React, Vue, or similar modern frameworks. Experience with component design, state management, hooks, and creating performant UI applications."}
- {"name":"SQL and Relational Databases","description":"Strong SQL expertise and deep understanding of relational database design, optimization, indexing strategies, and query performance. Experience with PostgreSQL, MySQL, or similar databases in production environments."}
- {"name":"System Design and Architecture","description":"Ability to design scalable, maintainable systems addressing non-functional requirements like performance, reliability, and security. Experience making architectural trade-offs and implementing patterns like caching, message queues, and microservices."}
- {"name":"LLM APIs and Frameworks (OpenAI, Claude, or similar)","description":"Practical experience integrating with and building upon modern LLM APIs. Familiarity with prompt engineering, token management, cost optimization, and reliable LLM usage patterns in production applications."}
- {"name":"Git and Version Control","description":"Proficiency with Git, branching strategies, code review workflows, and collaborative development practices. Comfortable with pull request processes and maintaining clean commit histories."}

### preferred

- {"name":"LangChain or LlamaIndex","description":"Experience with LangChain, LlamaIndex, or similar frameworks for building LLM applications. Familiarity with chains, agents, memory management, and retrieval-augmented generation patterns."}
- {"name":"Function Calling and Tool Integration","description":"Hands-on experience implementing tool calling mechanisms for LLMs, designing tool interfaces, and orchestrating multi-step agentic workflows. Understanding of how to reliably connect LLMs to external systems."}
- {"name":"Production ML Infrastructure","description":"Experience with MLOps practices, model serving infrastructure, deployment pipelines, monitoring ML systems in production, and managing technical debt in ML codebases. Familiarity with tools like Docker, Kubernetes, or orchestration platforms."}
- {"name":"React Query or State Management","description":"Advanced knowledge of client-side data fetching, caching strategies, and state management solutions. Experience with React Query, Redux, or Zustand for managing complex application state in frontend systems."}
- {"name":"WebSockets or Real-Time Communication","description":"Experience building real-time features using WebSockets, Server-Sent Events, or similar technologies. Understanding of bidirectional communication patterns needed for responsive agent monitoring and control interfaces."}
- {"name":"Testing Frameworks and Evaluation Systems","description":"Expertise designing comprehensive testing strategies, including unit tests, integration tests, and end-to-end tests. Experience building evaluation frameworks for AI systems including metrics, benchmarks, and automated testing pipelines."}
- {"name":"Cloud Platforms (AWS, GCP, or Azure)","description":"Solid experience deploying and managing applications on major cloud platforms. Familiarity with containerization, serverless functions, managed databases, and monitoring services relevant to AI workloads."}
- {"name":"Async Task Processing (Celery, Bull, or similar)","description":"Experience implementing asynchronous task queues and background job processing. Understanding of task scheduling, retry logic, and managing long-running operations suitable for agent execution."}
- {"name":"Observability and Monitoring","description":"Strong background in application observability including structured logging, metrics collection, distributed tracing, and monitoring dashboards. Experience setting up alerting for operational reliability in mission-critical systems."}
- {"name":"Human-in-the-Loop Workflow Design","description":"Practical experience designing systems that effectively combine AI automation with human oversight. Understanding of UX patterns for human validation, exception handling, and feedback loops in AI-driven workflows."}

## Tech stack

### tools

- {"name":"Docker","description":"Containerization for consistent deployment across environments. Used for packaging services and ensuring reproducible deployments of AI agents and backend systems."}
- {"name":"Kubernetes or Cloud Orchestration","description":"Container orchestration platform for managing deployment, scaling, and monitoring of AI services. Handles load balancing and ensures reliable operations at scale."}
- {"name":"Celery or Bull","description":"Task queue systems for asynchronous agent execution, background processing, and scheduled tasks. Enables reliable execution of AI operations without blocking request handlers."}
- {"name":"Git and GitHub","description":"Version control and collaboration platform. Used for code management, pull request workflows, and maintaining development practices."}
- {"name":"OpenAI API, Anthropic Claude API, or similar","description":"LLM provider APIs integrated into the agent platform. Used for running language models and tool calling mechanisms at scale."}

### others

- {"name":"Monitoring and Observability Platforms","description":"Tools like Datadog, New Relic, or Prometheus for tracking system performance, agent execution metrics, and operational health. Critical for maintaining reliability at scale."}
- {"name":"Testing Frameworks (pytest, Jest, Playwright)","description":"Comprehensive testing toolchain for unit tests, integration tests, and end-to-end testing. Ensures reliability of AI agent systems and frontend interfaces."}
- {"name":"CI/CD Pipelines (GitHub Actions, GitLab CI)","description":"Automated deployment pipelines ensuring code quality, testing, and reliable deployments. Enables rapid iteration while maintaining production stability."}
- {"name":"API Documentation Tools (Swagger/OpenAPI, Postman)","description":"Tools for documenting API contracts and enabling developer collaboration. FastAPI provides automatic Swagger documentation for API endpoints."}

### databases

- {"name":"PostgreSQL","description":"Primary relational database for storing agent configurations, execution logs, evaluation results, and operational data. Provides reliability and advanced query capabilities needed for complex agent management."}
- {"name":"Redis","description":"In-memory data store for caching, session management, real-time messaging, and async task queuing. Supports fast agent state lookups and real-time updates to monitoring interfaces."}
- {"name":"Vector Database (Pinecone, Weaviate, or similar)","description":"Optional specialized database for semantic search and retrieval-augmented generation features. Enables agents to retrieve relevant context from historical data and knowledge bases."}

### languages

- {"name":"Python","description":"Primary backend language for AI agent implementation, LLM integration, and system services. Used for FastAPI services, business logic, and AI framework implementation."}
- {"name":"TypeScript","description":"Frontend development language for building internal tools UI, monitoring dashboards, and agent management interfaces. Ensures type safety and better developer experience in complex client applications."}
- {"name":"JavaScript","description":"Supporting language for frontend and browser-based tooling. Used for real-time interactions and responsive UI components."}

### frameworks

- {"name":"FastAPI","description":"High-performance Python web framework for building REST APIs and backend services serving the Ops AI Platform. Enables rapid development with automatic API documentation and async request handling."}
- {"name":"React","description":"Frontend framework for building the user interface where operations teams create, test, and monitor AI agents. Used for building interactive dashboards and real-time monitoring capabilities."}
- {"name":"LangChain or LlamaIndex","description":"LLM application frameworks for implementing agent orchestration, prompt management, tool calling, and chain patterns. Simplifies building reliable AI agent systems."}
- {"name":"Next.js","description":"Optional full-stack framework for building internal tools with server-side rendering, API routes, and optimized performance. Useful for integrating frontend and backend seamlessly."}

## Benefits

### benefits

## Compensation

- **max:** 0
- **min:** 0
- **currency:** 
- **stockOptions:** false

## Interview process

### steps

## Full description
## **Health can’t wait**. 

Not for symptoms to get worse. Not for a six‑month appointment. Not for a system to catch up. But that’s exactly how healthcare works today. You wait, until you can’t.

Alan exists to end the wait.

Health is a universal right, and we believe this right can only become real when it’s coupled with prevention. We need to stop treating health as something we repair and start treating it as something we build, every day. It’s not solely a question of willpower. It’s the healthcare system itself that needs to work for everyone, in a sustainable way.

So we are building the **new standard in prevention insurance.** Alan is the first company that integrates insurance, prevention, and care into a single, acclaimed user experience.

We are on an incredible journey to build a **global leading company, with a** [**unique culture**](https://alan.com/en/careers). We already partner with 40K+ companies of all sizes, serving more than 1M+ members, and have reached €800M+ in ARR.

Prevention as the new norm. That's what we're building with our team of 1000+ people. If it speaks to you: we're hiring across France, Spain, Belgium, and Canada. And beyond.

# **🤖 Ops AI Platform team 🔀**

**We're building something that doesn't exist yet.**

Imagine a platform where AI agents autonomously handle operational work - connected to every internal and external tool, trained by operators themselves, running safely at scale. No engineers needed. No bottlenecks. Just agents that work.

That's what we're building. The **Ops AI Platform** will let our Ops team create, evolve, and monitor their own AI agents to automate thousands of tedious tasks. We aim to crack problems no one has solved at this scale.

The project **just launched**. You'd join at **ground zero** \- shaping the architecture, the product, the entire foundation.

If building the future of work from scratch excites you, this is it.

# **⭐ Our north star**

We’re building ops agents that work reliably and safely, without putting the engineering team on the critical path.

You’ll work at the intersection of product engineering and ML engineering. Our mission is to create the platform that enables building accurate and reliable AI agents, delivering an outstanding experience to our internal Ops team for the creation, iteration and monitoring of their agents, without requiring hard technical skills. Things we’re working on:

* **💬 Integrate agents at the heart of internal tools** \- UIs where Ops monitor and take action on concrete business situations. We want AI agents to become first-class citizens in this ecosystem, with context-aware chat modals, allowing users to review agents' reasoning, actions, and provide follow-up instructions - with instant impact on business data.
* **👥 Empower non-technical users to become autonomous** in the creation and maintenance of agents to automate operational tasks at scale: prompting, tools configuration, testing, datasets, replayability, evaluations
* 🔧 **Build a complete set of tools made available to AI agents**, connecting to internal and external capabilities: internal business data, external servers, external web dashboards without API, etc.
* **💯 Safety and accuracy at the core:** robust testing, stateful evaluation, progressive rollout, human-in-the-loop to validate sensitive actions, fine-grained permissions and limits

In 6 to 12 months, we plan to increase our scope by owning the AI platform that will power all agentic use cases at Alan - creating economies of scale thanks to common infrastructure and tooling.

If you’re excited by the idea of building the future of work, this is the team for you - we're at the start of the journey.

# **🎯 Is it you we’re looking for?**

We’re looking for **Product engineers with 3+ years of experience** who get excited about building state-of-the-art AI systems and applying them to real-world, high-stakes problems in operations.

* You’ll work at the frontier of LLMs, tool calling, human-in-the-loop, internal tools UX, multi-agent architectures, and see your work deployed in production, used by our ops team
* You’ll implement new capabilities for AI agents, as well as tooling to make ops autonomous on the creation, evolution, monitoring and evaluation of their agents
* You’ll work on making our system scale, going from a few dozen to tens of thousands of tasks automated daily
* You’ll have significant influence on system architecture and code quality
* You’ll mentor engineers, contribute to our product & engineering culture, and help build the team (including participating in hiring).

**You would be a good fit at Alan if most of this sounds like you:**

* Strong background in full-stack software engineering, systems architecture, with a spike in back-end engineering.
* Experience with traditional ML, or LLMs, or ML dev ops is a big plus
* Product-minded: you want your solutions to be used, and impactful
* Self-directed and pragmatic
* Humble and still willing to grow (no matter your seniority!)
* Collaborative, enthusiastic about teamwork, learning, and teaching
* Fluent in English (no need to speak French!)

But above all, we are looking for high potential and curiosity: make sure to show us this when you apply! Everything else is a bonus.

**For this opportunity, we are aiming to hire within the D-F level range.**

# 🙌 [Perks & Benefits](https://alan.com/en/careers/a/salary-equity)

At Alan, we believe that **being in good health is a basic need,** and it starts with our employees. This is why Alaners are provided with a stimulating environment and perks ensuring they are **happy, efficient and spend only high-quality time** with co-workers. 

**Therefore, we offer:**

* **Fair rewards**. Generous equity packages complement your base salary.
* **Flexible Office**. Amazing office space at our HQ, sponsored co-working hubs or a full-remote experience with home office equipment sponsorship, we want you to live where you’re the happiest.
* **All the tools you need**. Top of the range equipment: Macbook Pro, keyboard, laptop stand, monitor, and noise-canceling headphones.
* **Flexible vacation policy and flexible working hours**. Organize your time as you wish.
* **Delightful healthcare insurance:** Extremely comprehensive health insurance - 100% for you and your children, 90-100% for partners depending on your country _(permanent contracts only)_.
* **Transport**. Country-specific commuter benefits.
* **Learning & Training opportunities.** A highly flexible Training policy free books and budget to attend and speak at conferences if the opportunity arises.
* **Personal growth through coaching**: At Alan, coaching isn't just a perk -it's core to who we are. Every Alaner is paired with a dedicated coach from day one, who helps maximize their impact, nurture engagement, and navigate Alan's values to develop their full potential.[**Learn more about our coaching culture**](https://alan.com/en/blog/discover-alan/a/alan-culture-excellence-through-coaching)**.**
* **Parental leave.** Extended parental leave for all new parents.

## **Important note: we hire people, not roles.**

If you're excited about this opportunity but don't check every box, **we'd love to hear from you.** Everyone, no matter how underrepresented, should feel free to apply as it can only bring learnings or success.

**If you identify yourself as a woman**: Did you know that research shows women often apply only when meeting 100% of requirements?

**Remember, this is just a guide, not a checklist.**

We'll be thrilled to receive your application!

🔖 Check out our [About Alan](https://alan.com/about) and [Career](https://alan.com/careers) pages, as well as our [Medium](https://medium.com/alan), [blog](https://blog.alan.com/) and [Glassdoor page](https://www.glassdoor.com/Overview/Working-at-Alan-EI%5FIE1696043.11,15.htm) for more info.

**🔄 A quick note about the process**  
_Note: While you're applying for a specific area,, you may join a different engineering team based on where we think you'll have the most impact. Check out descriptions of other areas_ [_here_](https://www.notion.so/alaninsurance/Software-Engineering-Areas-Alan-2c61426e8be7805bacd2cdbc08c32640?source=copy%5Flink)_._