Senior ML Engineer: LLM Systems & RAG Pipelines

Oscar; Greater London; On-site; GBP 120,000 - 180,000; Full time

Benefits offered by this job

Central London office

Competitive compensation

Impactful work with financial services

Collaborative environment

Job summary

Oscar is seeking a Senior Software Engineer to design, build and operate LLM-powered workflows for an AI work-execution platform. You will work in Python/FastAPI with LangGraph and LangChain across model providers, focusing on low latency, auditability and cost control.

You will own production RAG pipelines, graph retrieval, and mentor engineers while collaborating with the Executive Committee. Role is based in London’s King’s Cross office with competitive compensation and a strong focus on

Qualifications

• 5+ years of software engineering experience.
• 2+ years running LLM/ML systems in production.
• Hands-on experience with an agent framework (LangGraph/LangChain).
• Production RAG experience with embeddings and vector databases.

Responsibilities

• Build multi-step agentic workflows with tool-calling and human-in-the-loop patterns.
• Integrate models from Anthropic, OpenAI and Bedrock, managing routing and cost.
• Own production RAG pipelines and GraphRAG on Neo4j.
• Measure latency, cost and quality for every model call.
• Apply GDPR-compliant guardrails and ship with FastAPI and PostgreSQL.

Skills

Python

LangGraph

LangChain

LLM systems

RAG pipelines

Education

Bachelor's degree in engineering or computer science

Tools

Neo4j

PostgreSQL

Qdrant

Weaviate

pgvector

Job description

Oscar is seeking a Senior Software Engineer to design, build and operate LLM-powered workflows for an AI work-execution platform. You will work in Python/FastAPI with LangGraph and LangChain across model providers, focusing on low latency, auditability and cost control.

You will own production RAG pipelines, graph retrieval, and mentor engineers while collaborating with the Executive Committee. Role is based in London’s King’s Cross office with competitive compensation and a strong focus on