• Initial 6 Month Contract | Potential To Extend
• Clayton Location | 3 Days On-Site & 2 Days WFH
• 3+ years ML/AI engineering with production LLM systems

The Role: The AI Engineer will build production LLM systems for a data transformation program. The AI Engineer will focus on designing the architecture and write the code, working collaboratively across Capability Leads and the Operations team.

The Responsibilities:

• Choose models, design RAG strategy, make cost/performance trade-offs
• Build data pipelines: ingestion, chunking, embeddings, retrieval, generation
• Design multi-step agentic workflows with tool integration (MCP-compatible)
• Implement automated and manual evaluation frameworks
• Configure guardrails, PII filters, and security controls
• Deploy containerised solutions with monitoring
• Document systems for handover

Skills & Experience Required:

• 5+ years of experience as an Engineer or Architect focused in building and delivering One or more shipped production LLM systems, while having the ability to explain technical decisions in terms of latency, cost, and accuracy is essential.
• Experience with Python, Docker, Terraform, CI/CD, Serverless Architecture such as ECS and Lambda is essential.
• Experience with LLM orchestration is essential. (e.g. LangChain, LlamaIndex, or similar).
• Experience with RAG implementation with vector databases is essential (e.g. pgvector, OpenSearch, Pinecone or FAISS).
• Experience with AI from AWS (Bedrock, SageMaker) and/or Azure (OpenAI, Azure ML) is essential.
• Prior experience with evaluation frameworks such as Promptfoo, Ragas, or custom is strongly encouraged.
• Security: KMS, VPC, private endpoints, OIDC.

What's in it for you:

• Initial 6 Month Contract | Potential To Extend
• Clayton Location | 3 Days On-Site & 2 Days WFH
• 3+ years ML/AI engineering with production LLM systems

Apply today and Jimmy Nguyen will reach out to disclose further information.