Engineering Team Lead — AI/LLM Platform & Full-Stack

Jobtailor; Greater London; On-site; GBP 90,000 - 130,000; Full time

Job summary

Savanta is seeking a hands-on engineering leader to head the Virtual Personas team, our synthetic personas platform for market research. You will own the product roadmap, mentor up to four engineers, and drive a cloud-first strategy.

You will develop full-stack solutions with Python/FastAPI and React/TypeScript, implement automated testing and CI gates, and harden AI features against prompt injection while working closely with customers to translate needs into scalable architecture.

Qualifications

• Experience leading agile rapid release iterations on AI/LLM-powered products.
• Extensive experience with Python and modern async web frameworks or closely related languages.
• Hands-on experience building or maintaining LLM-powered applications, incl. prompt design & multi-provider integration.
• Strong RDBMS experience, such as PostgreSQL.
• Comfort with document stores (MongoDB) and caching layers (Redis).
• Familiarity with AI-assisted development tools (Claude Code, Cursor, GitHub Copilot).

Responsibilities

• Lead agile rapid release iterations for AI/LLM-powered products.
• Deliver the product roadmap and set technical direction.
• Mentor up to four engineers in a cross-functional team.
• Embed automated testing and CI quality gates into the product.
• Interact with customers to translate needs into scalable architecture.

Skills

Agile leadership

Python development

Full-stack development

LLM application development

Automated testing

Tools

FastAPI

React

TypeScript

PostgreSQL

MongoDB

Redis

Async SQLAlchemy

CI quality gates

Prompt Design

Job description

Savanta is seeking a hands-on engineering leader to head the Virtual Personas team, our synthetic personas platform for market research. You will own the product roadmap, mentor up to four engineers, and drive a cloud-first strategy.

You will develop full-stack solutions with Python/FastAPI and React/TypeScript, implement automated testing and CI gates, and harden AI features against prompt injection while working closely with customers to translate needs into scalable architecture.