# Senior Software Engineer, AI Developer Tools
**Company:** [Docker](https://scaleengineer.com/companies/docker)
Senior Software Engineer role at Docker focusing on AI-powered developer tools and platform infrastructure. You'll design and operate production AI agents for developer productivity (code review, testing, deployment diagnostics), build self-service platform capabilities for teams to prototype and deploy their own AI tools, and contribute to reliable, secure AI systems. This position requires 6+ years of software engineering experience, hands-on LLM and AI agent development expertise, and strong backend/platform engineering fundamentals.
**Role:** Senior Software Engineer
**Seniority:** Senior
**Locations:** San Francisco, CA
**Remote:** yes
**Salary:** 160900–260700 USD
[Apply](https://jobs.ashbyhq.com/docker/48ef7134-5d54-4662-b8d3-a70b55eb9a58)
Canonical: https://scaleengineer.com/jobs/docker/senior-software-engineer-ai-developer-tools-48ef7134
---
## Responsibilities

- Design and Operate Production AI Agents: Build and operate production-grade AI agents that accelerate developer productivity, including code review assistants, automated test generators, deployment pipeline diagnostic agents, and on-call incident response automation. Ensure agents are reliable, observable, and measurably improve developer workflows.
- LLM and Agent Framework Integration: Integrate LLM providers (OpenAI, Anthropic, and others), agent orchestration frameworks, and MCP servers into reliable, production-ready developer tools. Implement prompt engineering best practices and validate AI outputs before deployment.
- Build and Operate Self-Service Platform Infrastructure: Develop and maintain platform capabilities including GitOps deployment pipelines (ArgoCD), Grafana-based observability integration, security controls, and cost management systems that enable teams across Docker to prototype, build, and deploy their own AI developer tools faster.
- Platform Reliability and Observability: Contribute to reliability, security, and performance standards for AI systems by defining SLOs, implementing monitoring and alerting, establishing incident response procedures, and improving runbooks to reduce time-to-resolution.
- Feature Design and Delivery: Shepherd features and services from vague requirements to production by asking clarifying questions about scale, users, and constraints, writing design documents, participating in design reviews, and iteratively shipping improvements.
- Infrastructure Integration: Build integrations between AI developer tools and existing Docker infrastructure including CI/CD pipelines, observability platforms, deployment systems, and internal developer tools to create seamless workflows.
- Code Review and Technical Mentoring: Conduct thorough code reviews using AI-assisted engineering practices, share learnings with the team, help newer engineers understand team patterns and best practices, and mentor others on AI-native development approaches.
- On-Call Operations and Incident Response: Participate in on-call rotation for owned services, respond to incidents affecting developer workflows, improve alerts and runbooks based on incident learnings, and help strengthen operational practices.
- Cross-Team Collaboration: Partner with Infrastructure, Security, Data, and product engineering teams to align on integrations, shared standards, and platform improvements. Help teams outside AI Developer Tools build and run their own tools on the platform.
- Adoption Metrics and Instrumentation: Instrument AI developer tools to measure adoption, effectiveness, and developer satisfaction. Track metrics that demonstrate tool value and guide product decisions.
- AI/LLM Landscape Monitoring: Keep current with emerging AI, LLM technologies, and agent framework innovations. Evaluate new tools and patterns for applicability to Docker's needs and share findings with the team.

## Requirements

### education

- {"name":"Computer Science or Engineering Degree","description":"Bachelor's degree in Computer Science, Engineering, or related field."}
- {"name":"Equivalent Practical Experience","description":"Equivalent practical software engineering experience demonstrating mastery of the required technical skills."}

### technical

- {"name":"LLM and AI Agent Development","description":"Hands-on experience building LLM-powered applications and AI agents. Practical working knowledge of LLM APIs (OpenAI, Anthropic, others), prompt engineering techniques, and agent orchestration frameworks."}
- {"name":"Backend Services and Distributed Systems","description":"Proven experience designing and operating scalable backend services, distributed systems architecture, and developer-facing platforms at production scale."}
- {"name":"Cloud-Native Infrastructure","description":"Strong expertise with Kubernetes orchestration, containerization, CI/CD pipeline architecture, GitOps patterns (ArgoCD), and cloud infrastructure deployment."}
- {"name":"Observability and Monitoring","description":"Working knowledge of observability systems including Grafana for metrics visualization, logging aggregation, distributed tracing, and SLO definition and monitoring."}
- {"name":"Programming Languages","description":"Proficiency in Go (preferred), Rust, Java, or Python with strong software engineering fundamentals including design patterns, testing strategies, and performance optimization."}
- {"name":"AI Developer Tools Development","description":"Experience building developer tools, platform systems, or internal tools that other engineers rely on. Understanding of developer experience design and adoption strategies."}
- {"name":"Security and Operational Practices","description":"Familiarity with security controls for production AI systems, operational best practices, and infrastructure-as-code approaches (Terraform, Pulumi)."}

### experience

- {"name":"6+ Years Production Software Engineering","description":"Minimum 6 years of software engineering experience designing, building, and operating production systems at scale."}
- {"name":"LLM and AI-Assisted Development","description":"Hands-on experience building LLM-powered applications, AI agents, or AI-assisted developer tools in production environments."}
- {"name":"Platform and Infrastructure Engineering","description":"Background in developer productivity, DevOps, SRE, or platform engineering with experience building internal tools and platforms."}
- {"name":"Ownership and Autonomous Work","description":"Demonstrated ownership mentality with ability to work autonomously in distributed, fast-moving environments. Experience taking features from requirements to production iteratively."}

## Skills

### required

- {"name":"LLM APIs and Prompt Engineering","description":"Proficient with OpenAI, Anthropic, and other LLM providers. Skilled in prompt engineering, few-shot learning, and prompt optimization techniques."}
- {"name":"Agent Orchestration Frameworks","description":"Working knowledge of agent frameworks and orchestration patterns for building reliable AI workflows."}
- {"name":"Go Programming Language","description":"Preferred primary language. Strong proficiency in Go with ability to write efficient, maintainable backend code."}
- {"name":"Python","description":"Proficiency in Python for AI/ML integration, scripting, and backend development."}
- {"name":"Kubernetes and Container Orchestration","description":"Deep expertise in Kubernetes deployment, configuration, scaling, and operational management."}
- {"name":"CI/CD Pipeline Design","description":"Experience designing and implementing robust CI/CD pipelines for production systems."}
- {"name":"Distributed Systems Architecture","description":"Strong understanding of distributed systems patterns, consistency models, and scalability principles."}
- {"name":"REST APIs and gRPC","description":"Proficiency in designing and implementing both REST and gRPC APIs for scalable backend services."}
- {"name":"Product Design Judgment","description":"Ability to weigh developer experience against technical trade-offs and ask clarifying questions before committing to designs."}
- {"name":"Remote Async Communication","description":"Excellent written and spoken communication skills suited to remote, asynchronous-first environments with clear documentation."}

### preferred

- {"name":"Model Context Protocol (MCP)","description":"Experience with MCP or similar AI agent integration standards and protocols."}
- {"name":"ArgoCD and GitOps","description":"Experience with GitOps deployment patterns and ArgoCD for declarative infrastructure management."}
- {"name":"Grafana Observability","description":"Hands-on experience building dashboards and implementing observability solutions in Grafana."}
- {"name":"Rust","description":"Proficiency in Rust for systems programming and performance-critical components."}
- {"name":"Infrastructure as Code","description":"Experience with Terraform, Pulumi, or similar IaC tools for reproducible infrastructure management."}
- {"name":"Open Source Contributions","description":"Contributions to open source AI tools, developer tooling, or platform engineering projects."}
- {"name":"AWS, GCP, and Azure","description":"Familiarity with major cloud platforms and their native services for building scalable applications."}
- {"name":"Production AI System Security","description":"Familiarity with security and operational practices specific to production AI systems and LLM applications."}

## Tech stack

### tools

- {"name":"Kubernetes","description":"Container orchestration platform for deploying and scaling AI developer tools at scale."}
- {"name":"Docker","description":"Containerization technology for packaging applications, including AI agents and platform services."}
- {"name":"Grafana","description":"Observability and visualization platform for monitoring metrics, logs, and system health."}
- {"name":"OpenAI API","description":"Large language model API for building AI-powered features and agents."}
- {"name":"Anthropic API","description":"Claude API for building AI-assisted development tools with advanced language understanding."}

### others

- {"name":"MCP (Model Context Protocol)","description":"Standard protocol for AI agent integration and context management across platforms."}
- {"name":"Terraform","description":"Infrastructure-as-code tool for provisioning and managing cloud resources consistently."}
- {"name":"Pulumi","description":"Infrastructure-as-code platform using programming languages for IaC automation."}
- {"name":"AWS, GCP, Azure","description":"Major cloud platforms for deploying globally distributed, scalable infrastructure."}

### databases

- {"name":"PostgreSQL","description":"Primary relational database for persistent state and transactional consistency."}
- {"name":"Redis","description":"In-memory data store for caching, session management, and real-time data processing."}

### languages

- {"name":"Go","description":"Primary backend language for building scalable, efficient microservices and platform components."}
- {"name":"Python","description":"Used for AI/LLM integration, agent orchestration, and backend scripting."}
- {"name":"Rust","description":"Systems programming for performance-critical infrastructure and container runtime optimization."}
- {"name":"Java","description":"Alternative backend language option for certain platform components."}

### frameworks

- {"name":"Agent Orchestration Frameworks","description":"Frameworks for building and managing AI agents, including patterns for task coordination and state management."}
- {"name":"ArgoCD","description":"GitOps continuous deployment framework for declarative infrastructure and application management."}
- {"name":"gRPC","description":"High-performance RPC framework for inter-service communication and API design."}

## Benefits

### benefits

- {"name":"Remote-First Work Environment","description":"Work from anywhere with offices in Seattle and Paris available for team connection and collaboration. Full flexibility to manage your schedule while delivering high-impact work."}
- {"name":"Generous Paid Time Off","description":"Unlimited PTO policy combined with designated quarterly Whaleness Days for recharge and a company-wide end-of-year Whaleness break to disconnect and rejuvenate."}
- {"name":"Home Office Support","description":"Equipment and environment stipend to set up a comfortable, productive home workspace tailored to your needs."}
- {"name":"Technology Stipend","description":"Monthly net stipend of $100 USD to support your work setup, software licenses, and professional development tools."}
- {"name":"Learning and Development","description":"Annual stipend for conferences, training courses, professional certifications, and continued education aligned with your growth goals."}
- {"name":"Equity Participation","description":"Full-time employees receive stock options and equity, allowing you to share in Docker's long-term success as the company grows."}
- {"name":"Parental Leave","description":"16 weeks of paid parental leave after six months of employment, supporting work-life balance and family needs."}
- {"name":"Comprehensive Health and Retirement Benefits","description":"Medical, dental, and retirement benefits vary by country. Docker provides competitive coverage across all markets."}
- {"name":"Paid Holidays","description":"Country-specific paid holidays and observances to ensure time with family and community."}
- {"name":"Docker Swag and Community","description":"Exclusive Docker merchandise and access to the global Docker developer community and events."}

## Compensation

- **max:** 260700
- **min:** 160900
- **currency:** USD
- **stockOptions:** true

## Interview process

### steps

## Full description
## **About Docker**

Docker has been one of the most loved brands in developer tooling, trusted by more than 20 million monthly users and over 20 billion container image pulls. From solo founders to the world's largest companies, developers rely on Docker to build, share, and run their applications across our suite of products including Docker Desktop, Docker Hub, and Docker Scout.  
  
We are a globally distributed, remote-first team building the tools that define how software gets built and delivered. As AI agents redefine software development, Docker is at the center of that shift, providing the sandboxed environments, verified images, and secure infrastructure that make autonomous workflows trustworthy by default.

\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_

Docker is looking for a **Senior Software Engineer** to build AI-powered developer tools and the platform behind them on our AI Developer Tools team. You will work at the intersection of AI, developer experience, and platform engineering, building tools that make Docker's engineers more productive and the platform that lets teams across Docker prototype, deploy, and scale their own AI developer tools.

As a Senior Engineer you will design, build, and operate:

**AI-Powered Developer Tools.** AI agents and tools that accelerate developer productivity, surface observability insights, and automate operational reviews. You will help teams adopt an AI-native way of working and speed up adoption of tools such as Claude Code and Codex. Examples include AI-powered code review and refactoring assistants, automated test generators and local environment setup tools, deployment pipeline diagnostic agents, and agents that simplify on-call work during incidents.

**Self-Service AI Developer Tools Platform.** Platform infrastructure that lets product and platform teams across Docker unblock themselves by prototyping, building, and deploying their own AI developer tools, using the patterns and standards the team sets.

You will report to the Senior Manager, AI Developer Tools, and work closely with the team's Principal and Staff engineers, product engineering teams, and platform teams across Docker.

# What Would Make Someone Successful in This Role

You are a strong, hands-on engineer who enjoys building at the intersection of AI, developer experience, and platform engineering. You have built software on top of LLMs and AI agents and have a good sense of what works in practice. You care about the people using your tools, and you can tell a tool developers love from one they put up with. You take a feature from a vague request to production: you ask the right questions about requirements, design it sensibly, ship it iteratively, and operate it afterward. You are comfortable in a fast-moving AI landscape and balance quality with pragmatism. You make the engineers around you better through thoughtful code review and by sharing what you learn.

# Responsibilities

**Building and Operating AI Developer Tools**

* Design, build, and operate production AI agents for developer productivity, including code review assistants, test generators, deployment diagnostics, and incident response automation
* Integrate LLM providers, agent orchestration frameworks, and MCP servers into reliable tools, following the team's patterns and standards
* Build systems that help Docker's engineers adopt AI-native development tools
* Build integrations between AI developer tools and existing developer infrastructure such as CI/CD pipelines, observability platforms, and deployment systems
* Instrument your tools so the team can measure adoption, effectiveness, and developer satisfaction

**Self-Service Platform**

* Build and improve platform capabilities, including deployment pipelines (ArgoCD/GitOps), observability integration (Grafana), security controls, and cost management, that help teams ship their own AI tools faster
* Help reduce time-to-production for new products from weeks to days
* Contribute to reliability, security, and performance standards for AI systems, including SLOs, monitoring, and incident response

**Design and Delivery**

* Take features and services from requirements to production. Ask about scale, users, and constraints before designing, and write down your assumptions
* Write clear design documents for the work you own, and participate in design reviews for the team
* Review code thoroughly and share what you learn with the rest of the team
* Take part in the team's on-call rotation, and help improve alerts, runbooks, and tooling so the next incident is easier
* Follow the AI-assisted engineering practices the team sets: use AI tools critically, validate their output, and stay accountable for what you ship

**Collaboration and Growth**

* Work with the Senior Manager and the team's Principal and Staff engineers to understand priorities and shape your work
* Partner with Infrastructure, Security, and Data teams on integrations and shared standards
* Help newer engineers get up to speed on the team's tools, patterns, and practices
* Keep up with emerging AI/LLM technologies and agent frameworks, and bring useful findings back to the team

# Qualifications

## Required

* 6+ years of software engineering experience building and operating production systems
* Hands-on experience building LLM-powered applications, AI agents, or AI-assisted developer tools
* Working knowledge of LLM APIs (OpenAI, Anthropic, and others), prompt engineering, agent orchestration frameworks, and practical uses of AI in software development workflows
* Experience building and operating scalable backend services, distributed systems, or developer-facing platforms
* Experience with cloud-native infrastructure, including Kubernetes, CI/CD pipelines, and observability systems
* Proficiency in Go (preferred), Rust, Java, or Python, with strong software engineering fundamentals
* Experience building developer tools, platform systems, or internal tools that other engineers rely on
* Good product judgment: you weigh developer experience and technical trade-offs, and you ask clarifying questions before committing to a design
* Clear written and spoken communication suited to a remote, async-first company
* Ownership mentality with a bias for action and iterative delivery in ambiguous, fast-moving environments
* Comfortable working autonomously in a distributed, remote-first team
* Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience

## Preferred

* Experience with MCP (Model Context Protocol) or similar AI agent integration standards
* Background in developer productivity, DevOps, SRE, or platform engineering
* Contributions to open source AI tools, developer tooling, or platform engineering projects
* Experience with GitOps deployment patterns (ArgoCD) or Grafana-based observability
* Familiarity with security and operational practices for production AI systems
* Experience with infrastructure-as-code (Terraform, Pulumi) and major cloud platforms (AWS, GCP, Azure)

# What to Expect

## First 30 Days

* Learn Docker's current AI and developer tooling landscape, the team's services, and the architecture decisions made so far
* Meet your teammates, including the Principal and Staff engineers, the Senior Manager, and key stakeholders in product engineering
* Ship a useful production change in your first weeks, using the team's AI-assisted engineering workflow
* Review existing AI tool prototypes and internal experiments to learn what is working and what is not
* Shadow on-call and learn the operational profile of the team's services

## First 90 Days

* Own a feature or service from design to production with measurable impact, such as part of an AI code review agent, a deployment diagnostic agent, or an on-call assistant
* Write the design document for work you own and take part in team design reviews
* Contribute to the self-service platform's deployment pipeline, observability integration, or security controls
* Take part in the on-call rotation

## First Year Outlook

* Be a go-to engineer for one or more of the team's AI tools or platform components
* Have shipped multiple production improvements that Docker engineers use every day, with adoption and effectiveness you can point to
* Have helped teams outside AI Developer Tools build and run their own tools on the platform
* Have taken on larger and more ambiguous work as your scope grows, and helped newer engineers do the same

**Docker considers visa sponsorship on a case-by-case basis based on business needs.**

**Compensation & Equity**

**United States:** $160,900 – $260,700 + equity

\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_

## **Posting Information**

* **Open vacancy:** This posting is for an existing open role.
* **AI in hiring:** Docker may use AI-assisted tools during our recruiting process.
* **Interview recordings:** Candidates will be invited to opt in to interview recordings to support interviewer calibration and consistent evaluations. Recordings are optional and require explicit consent.

\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_

## **Perks & Benefits**

* **Remote-first by design** – Work from your home, with offices in Seattle and Paris for connection and collaboration.
* **Flexibility that fits your life** – We trust you to manage your schedule while delivering great work.
* **Time to recharge** – Generous PTO, designated quarterly Whaleness Days, and a designated end-of-year Whaleness break.
* **Home office support** – Set up your workspace for comfort and success.
* **Technology stipend** – Equivalent to **US$100 net per month** to help support your work.
* **Learning & development** – Annual stipend for conferences, courses, certifications, and continued learning.
* **Parental leave** – 16 weeks of paid parental leave after six months of employment.
* **Equity for all full-time employees** – Share in Docker's long-term success as we continue to grow.
* **Comprehensive benefits** – Medical, retirement, and paid holidays vary by country.
* **Docker swag** – Because representing the whale never gets old.

_Docker is proud to be an equal opportunity employer. We are committed to building a team that reflects a broad range of backgrounds, experiences, and perspectives. We believe diverse teams build better products, make better decisions, and better serve our global community._

#LI-REMOTE