ML Engineer - Retrieval & Knowledge Platform

Scale; Greater London; On-site; GBP 85,000 - 125,000; Full time

Job summary

Scale GP (Scale Generative AI Platform) seeks a Machine Learning Engineer to own retrieval and knowledge representation systems, from research to production. You will work across knowledge bases, vector stores, RAG pipelines and context engines powering enterprise agents with measurable impact.

The role emphasizes building reliable backend data pipelines, collaborating with product, ML, and infra teams, and delivering experiments quickly with high quality feedback loops to customers.

Qualifications

• 5+ years of experience building and deploying ML/AI systems in production.
• Master’s or PhD in Computer Science, ML, AI, or equivalent practical experience.
• Strong understanding of retrieval systems, RAG, embeddings, vector indexing, and knowledge representation.
• Experience with knowledge representation, semantic search, or agentic systems.

Responsibilities

• Own ML components end to end—from research and prototyping through production deployment.
• Work on knowledge representation systems, including ontologies and knowledge graphs, to support structured reasoning over enterprise data.
• Design and implement RAG pipelines, including chunking, embedding, indexing, retrieval and reranking.
• Build and maintain integrations between retrieval and ML components and diverse enterprise data sources, vector databases, APIs and services.
• Develop context retrieval systems balancing recall, precision, latency and cost.

Skills

Python

Production ML

RAG

Embeddings

Knowledge graphs

Vector indexing

Retrieval systems

Semantic search

Testing & CI

Distributed systems

Education

Master’s or PhD in CS/ML

Tools

PyTorch

TensorFlow

Docker

Job description

Scale GP (Scale Generative AI Platform) seeks a Machine Learning Engineer to own retrieval and knowledge representation systems, from research to production. You will work across knowledge bases, vector stores, RAG pipelines and context engines powering enterprise agents with measurable impact.

The role emphasizes building reliable backend data pipelines, collaborating with product, ML, and infra teams, and delivering experiments quickly with high quality feedback loops to customers.