Founding Engineer, Agent Systems — AI Infrastructure Lead

C&D Talent Advisory - Academy; St Albans; On-site; GBP 130,000 - 170,000; Full time

Benefits offered by this job

EMI-eligible equity

London office

On-site facilities

Job summary

TechTree is recruiting for a founding engineer to join an on-site role in London, focusing on building a production-grade agent platform for AI-native risk infrastructure. You will own the orchestration, tool-calling, and reliability frameworks while shaping the engineering standards for ship-ready AI features.

The role targets mid-senior level engineers with 6–7+ years of experience, strong backend skills, and a track record of shipping customer-facing AI systems. Equity is included.

Qualifications

• Minimum background in backend software engineering and ownership of production features.
• Experience shipping production LLM-powered features (1–2+ years).
• Strong TypeScript or Node.js experience, with familiarity in building customer-facing AI systems.
• Hands-on experience with agent frameworks and multi-step orchestration.
• Experience with AI evaluation infrastructure, data curation and regression testing.
• Understanding of reliability patterns, idempotency, and asynchronous processing.

Responsibilities

• Build and evolve the core agent orchestration platform.
• Design multi-step agent workflows and tool-calling systems.
• Develop secure sandboxing for agent execution and defense mechanisms.
• Implement production evaluation frameworks for high-stakes outputs.
• Own prompt versioning and AI-quality infrastructure.
• Define internal standards for production AI quality and ship/no-ship decisions.

Skills

Backend engineering

LLM features

TypeScript

Node.js

React

Tool calling

Asynchronous systems

Queues

Reliability engineering

Tools

Anthrop ic APIs

OpenAI APIs

Agent frameworks

Terraform

Postgres

Azure

Docker

Job description

TechTree is recruiting for a founding engineer to join an on-site role in London, focusing on building a production-grade agent platform for AI-native risk infrastructure. You will own the orchestration, tool-calling, and reliability frameworks while shaping the engineering standards for ship-ready AI features.

The role targets mid-senior level engineers with 6–7+ years of experience, strong backend skills, and a track record of shipping customer-facing AI systems. Equity is included.