AI/LLM Engineer (Contract) - RAG Implementation | London (Mostly Remote) - Outside IR35 - Jan Start
We're seeking a skilled AI/LLM Engineer to help deliver Retrieval Augmented Generation (RAG) solutions for a major client project in London.
This is a hands-on contract role suited to someone with strong implementation skills who can build reliable, production-ready AI systems on AWS.
3 months initially - Will certainly extend
Market rate
The Role
You'll play a key role in designing, building, and deploying advanced AI capabilities, working closely with technical and product teams. This position focuses on execution and delivery - developing scalable, secure solutions while contributing to best practices across the AI stack.
What You'll Do
- Design, build, and deploy RAG-based AI solutions
- Develop agentic workflows and intelligent automation capabilities
- Collaborate with architects to ensure sound AI design and integration
- Build and maintain scalable ML applications on AWS
- Implement ML Ops pipelines for training, deployment, and monitoring
- Evaluate and compare AI solutions to identify optimal approaches
- Ensure security, compliance, and reliability of production systems
- Contribute to establishing good engineering practices for AI delivery
What You'll Bring
- Proven experience developing and deploying RAG solutions in production
- Strong background in LLM and agentic system development
- Familiarity with MCP or similar model control frameworks
- Hands-on experience with ML Ops tools and workflows (CI/CD, model life cycle, monitoring)
- Understanding of security and governance in AI systems
- Solid experience with AWS infrastructure and services
- Clear communication skills and ability to collaborate effectively with cross-functional teams