About the Role
This is a senior, hands-on role for an engineer who has already shipped LLM systems to production and understands what it takes to run them reliably where mistakes have real financial and regulatory consequences.
5+ years in software engineering, with 2+ years shipping LLM/GenAI systems to production.
Strong Python and hands-on experience with LLM orchestration
RAG in depth – embeddings, vector stores, retrieval quality, chunking, and how to evaluate all of it.
Key Responsibilities
- Evaluation-first mindset – you build measurement into LLM systems rather than shipping on vibes.
- Solid ML grounding – transformer architectures, tokenisation, context windows, and their practical trade-offs.
- Production cloud – AWS or GCP, containers, CI/CD, and infrastructure-as-code for reliable, observable services.
- Regulated domain – fintech, payments, or another compliance-heavy environment.
How to Apply
More jobs at get9to5jobs.com