Supporting a major enterprise AI transformation programme
12 month contract
Inside IR35
I’m looking for Machine Learning Engineers (and Senior Data Scientists with strong engineering capability) who have real, hands‑on experience building GenAI applications end‑to‑end. Not just prototypes, but production systems.
This is a full‑stack ML Engineering role where you’ll design, build, deploy, and monitor GenAI applications that integrate LLMs as part of a wider system.
You’ll be working on:
- Building production‑grade GenAI applications using Python
- Developing LLM‑powered systems with LangChain, LangSmith, and modern Python libraries
- Designing and implementing RAG pipelines, vector stores, and retrieval logic
- Building agentic workflows, tool‑calling, and multi‑step reasoning systems
- Implementing guardrails, safety layers, and controls
- Designing monitoring for latency, drift, hallucinations, cost, and safety signals
- Integrating LLMs into broader application architectures (APIs, services, orchestration)
We’re looking for people who have:
- Delivered real GenAI applications into production, not just PoCs
- Experience with LangChain, LangSmith, LlamaIndex, or similar frameworks
- Deep understanding of LLM behaviour, prompting, evaluation, and optimisation
- Experience building monitoring, logging, and guardrail frameworks
- Ability to work across the stack: data, model, application, and infrastructure
- Strong communication skills and ability to work with product, engineering, and business teams
This is ideal for ML Engineers who love building end‑to‑end systems, not just models. People who can take a GenAI idea from concept to production and own the full lifecycle.
If you’ve built and shipped GenAI applications and want to work on high‑impact, enterprise‑scale projects, please apply.
#J-18808-Ljbffr…