Applied AI Engineer, Agents & Automations

Machine Learning Engineer · Mid · Full Time · Remote

Europe · RemoteUSD 150k – 210k2w ago
Apply for this role

Opens Cohere's application page

Role

What you'll do.

Applied AI Engineer specializing in enterprise AI agents and automations, working on Cohere's North platform to build production-ready AI experiences that help users create, configure, and improve AI-powered workflows. This role bridges product engineering, machine learning, and user experience design, requiring expertise in LLM-powered systems, agent architecture, evaluation frameworks, and production reliability to deliver secure, enterprise-grade AI solutions.

Responsibilities

  • Build AI-Powered Product Experiences: Design and develop AI-powered product surfaces within the North workspace platform that enable users to create, configure, evaluate, and iteratively improve AI agent workflows. Focus on translating frontier language model capabilities into intuitive user-facing systems that solve real enterprise challenges.
  • Design Human-AI Collaboration Interfaces: Create new interaction patterns and workflow builders for users to collaborate with AI agents, including proactive assistants, review flows, and inspection interfaces. Architect these interfaces to make agent behavior transparent, steerable, and trustworthy in production enterprise environments.
  • Build Evaluation and Observability Systems: Develop comprehensive eval frameworks, observability pipelines, and feedback mechanisms that measure AI experience success in real enterprise workflows. Create metrics and instrumentation that track both technical performance and business outcomes to guide continuous improvement.
  • Improve AI Reliability Through Systematic Optimization: Enhance AI system reliability through multi-faceted optimization including prompt engineering, context construction, tool-use strategies, product design refinements, instrumentation enhancements, and feedback loop implementation. Balance tradeoffs between model capability, product design, and operational complexity.
  • Convert Production Insights into Systematic Improvements: Translate production failures, user feedback, and real-task data into measurable product improvements, expanded eval suites, regression tests, and actionable signals for modeling teams. Own the full feedback cycle from failure detection to solution validation.
  • Collaborate Across Organizational Functions: Partner closely with modeling researchers, product managers, designers, customer success teams, and domain experts to define success criteria for specific workflows, validate solutions in real-world contexts, and align technical decisions with business outcomes.
  • Make Strategic Technical Decisions: Evaluate workflow requirements and determine optimal technical approaches, deciding when workflows need constrained product experiences, improved model interfaces, strengthened evaluation suites, or deeper modeling investments. Balance user needs against technical feasibility and resource constraints.
  • Own End-to-End Problem Spaces: Take ownership of ambiguous, complex problems spanning multiple system boundaries, from natural language workflow automation to multi-step agent eval creation to agent behavior transparency. Drive solutions from problem definition through production deployment and iterative refinement.

Qualifications

What we look for.

Technical

  • Production LLM System Experience

    Shipped and maintained LLM-powered, agent-powered, or AI-assisted product experiences in production environments. Demonstrated ability to iterate on deployed systems based on real-world user feedback and production metrics.

  • Full-Stack Software Engineering

    Strong foundation across backend systems, user-facing product development, data pipelines, evaluation frameworks, and model behavior. Comfortable working end-to-end from API design through frontend implementation to production monitoring.

  • AI Agent Architecture

    Understanding of agent design patterns, tool-use strategies, multi-step reasoning, and workflow orchestration. Ability to debug complex agent failures and optimize for reliability in real-world contexts.

  • Evaluation Framework Design

    Experience building evaluation systems for AI systems, including designing meaningful metrics, creating test suites, implementing feedback mechanisms, and interpreting evaluation results to guide product decisions.

  • Debugging Complex Systems

    Proficiency debugging distributed systems failures, tracing issues across model outputs, product logic, data pipelines, and user interactions. Strong problem-solving skills for ambiguous, multi-faceted issues.

Education

  • Bachelor's Degree in Computer Science or Related Field

    Formal foundation in computer science, software engineering, or equivalent technical discipline. Strong fundamentals in algorithms, data structures, and software architecture.

Experience

  • LLM Product Development

    3+ years building and iterating on LLM-based or AI-assisted product features in production, with demonstrated ability to improve product quality based on user feedback and production data.

  • Cross-Functional Collaboration

    Experience working across product, design, ML research, and customer-facing teams. Demonstrated ability to translate between technical and non-technical stakeholders and align diverse perspectives.

  • Production System Ownership

    History of owning systems from design through deployment to production, including responsibility for reliability, performance, and user satisfaction metrics.

Skills

Required

  • Python

    Core programming language for implementing AI systems, data processing pipelines, and backend services in modern LLM applications.

  • LLM APIs and Frameworks

    Hands-on experience with language model APIs (OpenAI, Anthropic, Cohere) and LLM frameworks like LangChain, LlamaIndex, or similar tools for building agentic systems.

  • Prompt Engineering

    Ability to craft, iterate, and optimize prompts for complex multi-step tasks, few-shot learning patterns, and tool-use scenarios. Understanding of prompt patterns for reliability and consistency.

  • System Design

    Ability to design scalable, reliable systems spanning frontend interfaces, backend APIs, data pipelines, and evaluation loops. Experience with distributed system tradeoffs.

  • Product-Oriented Problem Solving

    Thinking in terms of user outcomes and system behavior rather than isolated metrics. Ability to consider full user workflows and system reliability when making technical decisions.

Preferred

  • TypeScript/JavaScript

    Nice to have

    Frontend development experience for building user interfaces that interact with AI systems, useful for product surface design and prototyping.

  • React

    Nice to have

    Modern frontend framework experience for building responsive, interactive interfaces for AI collaboration and workflow configuration.

  • Agent Framework Development

    Nice to have

    Experience building or contributing to agent frameworks, orchestration systems, or agentic architecture components.

  • Data Science and Analytics

    Nice to have

    Proficiency with SQL, data analysis, and statistical methods for building evaluation systems and extracting insights from production data.

  • Cloud Platforms

    Nice to have

    Experience with cloud infrastructure (AWS, GCP, Azure) for deploying and scaling AI applications.

  • Enterprise Software

    Nice to have

    Understanding of enterprise software requirements including security, compliance, multi-tenancy, and integration with existing business systems.

Tech stack

Languages

PythonTypeScript

Frameworks

LangChainLlamaIndexReact

Databases

Vector DatabasesPostgreSQL

Tools

LLM APIsEvaluation and Monitoring ToolsVersion Control

Other

Prompt EngineeringAgent Architecture PatternsEvaluation Frameworks

Compensation

Pay and benefits.

Base·USD 150,000 – 210,000

Equity·Stock options

Benefits

  • Comprehensive Health Coverage

    Full health and dental benefits with a dedicated mental health budget, ensuring holistic wellness support for you and your family.

  • Retirement Planning

    RRSP matching for Canadian employees, 401K for US employees, and Pension Scheme for UK employees, supporting long-term financial security.

  • Premium Parental Leave

    100% salary top-up for up to 6 months of parental leave for either parent, supporting work-life balance during important life events.

  • Generous Paid Time Off

    6 weeks of paid vacation (30 working days annually), providing substantial time for rest, travel, and personal pursuits.

  • Professional Development

    Education and learning stipend for conferences, courses, coaching, and continuous skill development in rapidly evolving AI landscape.

  • Annual Enrichment Benefits

    Budget allocations for arts and culture, fitness and wellness programs, quality time, and workspace improvement credits to enhance life quality.

  • Weekly Lunch Stipend

    USD $75/GBP £75 weekly lunch stipend (or equivalent in local currency) supporting daily nutrition and workplace convenience.

  • Office and Remote Benefits

    Co-working benefit for remote employees in any city, $500 home office stipend to establish productive workspace, plus travel budget to visit company offices.

  • Global Offsite

    Annual company offsite bringing global team together for collaboration, team building, and strategic alignment.

Process

Interview steps.

  1. 01

    Initial Screening

    Recruiter review of application materials and background. AI-enabled screening tools may be used to assess alignment with role criteria, though human review is prioritized.

  2. 02

    Technical Phone Screen

    Conversation with engineering team member covering your experience with LLM systems, production AI development, and approach to solving ambiguous problems.

  3. 03

    Product and System Design Discussion

    Collaborative session exploring how you'd approach designing AI product experiences, evaluation frameworks, and production systems. Discussion of past projects and decision-making process.

  4. 04

    Technical Interview

    In-depth technical discussion covering software engineering fundamentals, system design, debugging complex problems, and real-world AI system challenges.

  5. 05

    Cross-Functional Interview

    Conversation with cross-functional partners (product, design, or research) to assess collaboration style and ability to work across organizational boundaries.

  6. 06

    Final Discussion

    Conversation with engineering leadership to discuss role expectations, growth opportunities, team dynamics, and long-term career development within Cohere.

Full posting

Original listing.

Who are we?

Cohere is the leading security-first enterprise AI company. We build cutting-edge foundation AI models and end-to-end products that are designed to solve real-world business problems.

We’re training and deploying frontier models for enterprises who are building AI systems. We believe that our work is instrumental to the widespread adoption of AI and we are looking for folks that want to be part of that.

We obsess over what we build. Each one of us is responsible for contributing to increasing the capabilities of our models and the value they drive for our customers. Cohere is a team of researchers, engineers, designers, and more, who are all passionate about their craft.

We are a global technology company headquartered in Toronto with key offices in London, New York City, San Francisco, Montreal, Paris, Berlin and Seoul. Join us!


Why this role?

North is Cohere's cutting-edge AI workspace platform, designed to revolutionize the way enterprises utilize AI. It offers a secure and customizable environment, allowing companies to deploy AI while maintaining control over sensitive data. North integrates seamlessly with existing workflows, providing a trusted platform that connects AI agents with workplace tools and applications.

Some of our most important work is making the agents and AI-powered experiences inside North genuinely useful in the workflows customers rely on every day. These systems become valuable when users can build with them, steer them, inspect their work, recover from errors, and trust them to complete messy tasks inside real enterprise environments.

This role is about making those AI experiences reliable, useful, and production-ready. You’ll work with product engineering, modelling and design to turn model capability into reliable, user-facing systems: agent builders, eval frameworks, proactive intelligence, and new interfaces for collaborating with AI. Sometimes that means shipping a new product surface, sometimes a better eval or feedback loop, sometimes prompt and context experiments, and sometimes redesigning the workflow so the model is being asked to do the right thing.


As an Applied AI Engineer, Agents & Automations, you will:

  • Build AI-powered product experiences that help users create, configure, evaluate, and improve workflows across North.

  • Design and ship new interfaces for interacting with models, including workflow builders, proactive assistants, review flows, and other human-AI collaboration patterns.

  • Build eval, observability, and feedback systems that measure whether AI experiences succeed in real enterprise workflows.

  • Improve AI reliability through product design, prompting, context construction, tool-use strategies, instrumentation, and feedback loops.

  • Turn production failures, user feedback, and real-task data into better product behavior, stronger eval suites, regression tests, and signals for modelling.

  • Work closely with modelling, product, design, customer teams, and domain experts to define what “good” means for specific workflows and ship measurable improvements.

  • Help decide when a workflow needs a more constrained product experience, a better model interface, a stronger eval, or a deeper modelling investment.

Example problems you might work on include helping users build AI automations from natural language, creating evals for multi-step agent workflows, adding proactive intelligence inside the product, or creating interfaces that make agent behavior easier to inspect, steer, and trust.


You may be a good fit if:

  • You have shipped LLM-powered, agent-powered, or AI-assisted product experiences into production, and improved them based on real-world feedback.

  • You are a strong software engineer who enjoys working across backend systems, user-facing product, data, evals, and model behavior.

  • You think in terms of user outcomes and system behavior, not just model metrics.

  • You have strong product taste and care about how the interface, workflow, and model work together to help users succeed.

  • You enjoy debugging messy real-world failures and turning what you learn from production, user testing, and evals into durable improvements.

  • You enjoy owning ambiguous problems end-to-end and working across system boundaries to ship something genuinely useful.

Full-Time Employees at Cohere enjoy these Perks:

  • A weekly lunch stipend of $75/£75 or equivalent in your local currency for lunch.

  • Full health and dental benefits, including a separate budget for mental health.

  • RRSP matching, 401K, Pension Scheme.

  • 100% Parental Leave top-up for up to 6 months, for either parent.

  • Annual enrichment benefits:

    Arts & culture, fitness/wellness, quality time, and a workspace improvement credit.

    Education & learning stipend for conferences, courses, and coaching.

  • 6 weeks of paid vacation (30 working days!)

  • Budget for traveling to other offices if you are remote, plus an annual company offsite.

How and Where We Work:

  • Cohere is remote-friendly, but we also have offices in Toronto, London, New York City, San Francisco, Montreal, Paris, Berlin and Seoul with more opening soon.

  • For those in the office: a daily lunch program, plenty of snacks, and regular community and social events.

  • For those not near an office: a co-working benefit so you can work alongside others in your city.

  • Everyone receives a $500 home office stipend to set up your workspace properly.

If any of the above doesn’t line up exactly with your experience, we still encourage you to apply.


We strive to create an inclusive work environment for all; we welcome applicants from all backgrounds and are committed to providing equal opportunities. Should you require any accommodations during the recruitment process, please submit an Accommodations Request Form, and we will work together to meet your needs.

We may use AI-enabled tools to screen and assess applicants against the criteria for this position. This helps our recruiters identify potentially qualified candidates, but it doesn't limit the applications our recruiters may review or consider.

Beware of Scams: Cohere will never ask for payment or third-party services (e.g., CV writing) as part of our hiring process. All legitimate roles are listed on the Cohere careers page and LinkedIn only, with all communications from Cohere employees coming from an @cohere.com or @cw.cohere email alias. If jobs are viewed on other sites then please verify these through our official careers page.

Redirects to Cohere's application page.

Other roles

More at Cohere.

View all 26 roles