Senior Python Engineer (Data Engineering & AI Agents)

Salary: £46,000 - 50,000 per year

Requirements:

• We have 6+ years building production software in Python, with strong engineering fundamentals in testing, performance, and clean design.
• We have solid data engineering experience, including SQL, columnar formats such as Parquet, pipeline design, and handling datasets large enough that naive approaches do not scale.
• We have hands-on experience with at least one analytical or query engine such as DuckDB, Trino, Spark, or ClickHouse.
• We have real experience building LLM or agent applications, including retrieval (RAG), vector databases, and tool or function calling.
• We have a working understanding of data governance, including cataloguing, metadata, lineage, and access control (RBAC / ABAC).
• We have an instinct for data quality and trustworthy golden sources.
• We have financial services or capital markets experience, such as market data, positions, reference data, or time-series stores, which would be a plus.
• We have experience in on-premise or regulated environments and their constraints, such as data residency, auditability, and golden copy never moves, which would be a plus.
• We have familiarity with semantic layers, knowledge graphs, and entity resolution, which would be a plus.
• We have exposure to policy-as-code such as OPA or data-access platforms, which would be a plus.
• We have awareness of how AI agents are secured, including identity, scoped access, evaluation, and monitoring, which would be a plus.
• We have consulting or client-facing / pre-sales experience, which would be a plus.

Responsibilities:

• We build production-grade Python services and data pipelines over large data stores, including columnar, time-series, and relational systems, as well as the queries that join across them.
• We select and implement the right query or analytical engine for each workload rather than defaulting to one.
• We build catalogue, metadata, lineage, and semantic layers that make data discoverable and consistently understood across teams.
• We implement access control that travels with the data, fusing sensitivity and licensing scope and enforcing it at the point of use, including for AI agents.
• We build agent-facing data access, including retrieval (RAG), vector search, and APIs / MCP servers, with permissions applied before context reaches the model.
• We apply LLMs pragmatically to data work, such as metadata generation, classification, and entity resolution, with humans in the loop, and we evaluate the quality of what the agents produce.
• We help keep data trustworthy by establishing golden sources, deduplication, and data-quality checks at the source.
• We contribute to discovery and solutioning by assessing current state, weighing build-vs-adopt, and shaping pragmatic, costed plans.

Technologies:

• AI
• AI Agents
• ClickHouse
• LLM
• MCP
• Python
• RAG
• RBAC
• SQL
• Security
• Spark

More:

Our client is a leading global investment management company headquartered in London, managing over $228 billion in assets. The firm is known for quantitative investing, systematic strategies, and technology-driven asset management, with data science, ML, and AI playing a key role in its research and investment processes. Our work focuses on two key areas for secure, scalable AI adoption: Agentic Security and AI-Ready Data Foundations. The goal is to make large on-premise data estates accessible, understandable, traceable, and properly permissioned for AI agents. This is a hands-on senior role for a strong Python engineer with solid data engineering experience and practical exposure to AI agents. You will build catalogue, semantic, entitlement, and analytical layers that enable agents to work with enterprise data safely and effectively.

last updated 35 week of 2026