Senior ML Engineer: RAG, Knowledge Graphs & Production

scaleai; Greater London; On-site; GBP 90,000 - 120,000; Full time

Job summary

Scale AI seeks a Machine Learning Engineer in London to own end-to-end platform development for agentic AI. You will work on knowledge representation systems, RAG pipelines, and context engines powering enterprise solutions.

You will build reliable data pipelines and ML integrations, balancing recall, latency and cost while collaborating with product and infrastructure teams to deliver impact at scale.

Qualifications

• 5+ years of experience building and deploying ML/AI systems for real-world, production use cases.
• Master's or PhD in Computer Science, Machine Learning, AI, or equivalent practical experience.
• Deep, hands-on understanding of retrieval systems, RAG, embeddings, vector indexing, knowledge representation, and semantic search.
• Proficiency in Python, writing production-quality, testable code.

Responsibilities

• Own large areas of the platform end to end, from design through to 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 that balance recall, precision, latency, and cost.
• Build evaluation frameworks, datasets, and metrics to measure retrieval quality, context relevance, and end to end agent performance.
• Build reliable backend services and data pipelines that support ML and LLM components in production.
• Deliver experiments and new capabilities quickly, maintaining high quality and tight feedback loops with customers.
• Collaborate across product, ML, and infrastructure teams to shape the direction of the platform.

Skills

Python

RAG

Knowledge graphs

Embeddings

Vector indexing

Semantic search

Production deployment

Education

Master's or PhD in Computer Science / ML / AI

Tools

APIs

Vector databases

Job description

Scale AI seeks a Machine Learning Engineer in London to own end-to-end platform development for agentic AI. You will work on knowledge representation systems, RAG pipelines, and context engines powering enterprise solutions.

You will build reliable data pipelines and ML integrations, balancing recall, latency and cost while collaborating with product and infrastructure teams to deliver impact at scale.