Join a forward-thinking engineering team focused on advancing the Llama Stack project with a strong emphasis on reliability, automation, and enterprise integration. In this role, you'll play a key part in shaping the core infrastructure that supports agentic and generative AI applications, ensuring robustness through comprehensive testing and scalable design.
What You'll Do
- Work alongside engineers, product specialists, and UX professionals to define functional requirements and translate them into resilient software solutions
- Design and implement automated testing strategies—including unit, integration, and end-to-end workflows—to ensure system stability and performance
- Manage and optimize CI/CD pipelines in GitHub, maintaining high standards for code quality across upstream and downstream environments
- Use AI-powered code review tools to detect bugs, enforce best practices, and improve overall code health
- Apply AI-driven methods to generate test cases, uncover edge conditions, and expand test coverage efficiently
- Develop and maintain clear technical documentation for APIs and developer tooling, supporting both internal and external users
- Partner with technical writers to ensure downstream documentation meets real-world usability standards
What We’re Looking For
- At least a decade of hands-on Python development, with strong fluency in writing clean, maintainable code
- Extensive experience with Bash or Shell scripting
- Proven background in test automation, quality engineering, and building reliable software pipelines
- Solid understanding of distributed systems architecture and performance at scale
- Direct experience developing agentic systems, RAG implementations, MCP integrations, or applications using large language models
- Expertise in GitHub Actions or similar CI/CD platforms for automating software delivery
- Deep familiarity with testing frameworks such as PyTest for functional and end-to-end validation
- Working knowledge of containerization technologies, including Kubernetes and OpenShift
- Experience deploying and managing infrastructure in cloud or on-prem environments
- Aptitude for rapidly learning and applying new technologies and methodologies
Nice to Have
- Background in security, observability, performance tuning, or large-scale system operations
- Familiarity with DevOps practices, agile workflows, or issue tracking tools like Jira
- Exposure to AI/ML frameworks including LlamaStack, LangChain, PyTorch, LLaMA.cpp, vLLM, LangGraph, or Kubeflow
Work Environment
This position supports flexible working arrangements across the EMEA region, with options for remote, hybrid, or office-based setups depending on role needs. We value autonomy, transparency, and inclusive collaboration—core principles that guide how we build both software and teams.
Our Culture
We foster an open, inclusive environment where diverse perspectives drive innovation. Everyone is encouraged to contribute ideas, challenge assumptions, and solve complex problems. Our culture emphasizes collaboration, equity, and access—ensuring all voices are heard and valued.
Equal Opportunity
We consider all applicants without discrimination based on race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, veteran status, or any other protected characteristic under applicable law.
