Python Engineer

In this Python Engineer role, you will build production-grade backend services with FastAPI and asynchronous Python, and integrate LLM capabilities into real applications for public sector programs. You’ll drive practical AI solutions such as RAG and document intelligence, balancing latency, cost and reliability in live environments. You will collaborate with architects, consultants and stakeholders to translate operational problems into scalable AI services, with a focus on security, testing and observability. This opportunity combines deep technical work with consultancy exposure on high-impact public sector challenges.

• Engineer Python backend services and APIs using FastAPI and async patterns
• Design and integrate LLM capabilities with OpenAI/Azure OpenAI or similar foundation models
• Build RAG, enterprise search and document intelligence solutions using embeddings and vector databases
• Develop prompt strategies with production considerations (latency, retries, cost, rate limits)
• Explore agentic workflows and LLM orchestration (LangChain or similar)
• Collaborate with consultants and stakeholders to translate operational problems into AI solutions
• Improve security, testing, observability and reliability of deployed applications

• 5+ years of commercial Python engineering experience, including production backends
• Strong FastAPI, REST API, async Python, PostgreSQL, and SQL experience
• Demonstrable experience integrating LLMs into real applications (not just prototypes)
• Strong Docker, Kubernetes/OpenShift, CI/CD and pytest knowledge
• Experience with large codebases and safe service evolution
• Knowledge of Azure, RAG, pgvector, Chroma, FAISS, Entra ID, OAuth/OIDC, Redis, Terraform, Prometheus or OpenTelemetry

• Effective collaboration with cross-functional teams
• Stakeholder communication and translation of problems into AI solutions
• Problem solving with a bias toward pragmatic production-ready results
• FastAPI
• REST API
• async Python