Lead AI Engineer - Python - Agentic & LLM frameworks - Remote
This role sits within an AI engineering team building and scaling production grade content generation systems. You will work directly on agentic workflows and LLM pipelines, contributing code and driving technical decisions across the full delivery lifecycle. The environment is fast moving, with close collaboration between engineering and AI research and development.
Responsibilities:
- Design, develop, and optimise agentic workflows using Python and LLM frameworks including CrewAI, LangGraph, and LangChain
- Operationalise AI models and LLM outputs into scalable production services built on Azure and AWS infrastructure
- Implement LLM observability, evaluation benchmarks, and regression detection using tools such as Langfuse, OpenLit, and New Relic
- Own unit and integration test creation as part of the development workflow, in line with a shift left quality approach
- Build and maintain CI/CD pipelines and contribute to SDLC best practices across the team
- Integrate and manage cloud resources across Azure Container Apps, Service Bus, and Blob Storage, with AWS exposure
Key Skills:
- Strong Python development experience with FastAPI in production environments
- Hands on experience with agentic and LLM frameworks, specifically CrewAI, LangGraph, or LangChain
- Production LLM experience including prompt engineering, model evaluation, and deployment via Azure OpenAI or Google Vertex AI
- Practical knowledge of Azure services and familiarity with AWS
- Solid understanding of CI/CD, Docker, and DevOps practices
Desirable Skills:
- Experience with ML and NLP tooling such as PyTorch, Hugging Face Transformers, or spaCy
- Working knowledge of Go sufficient to read and maintain existing services
- Kubernetes experience
- Familiarity with LLM observability tools including Langfuse or OpenLit
