Production AI Engineer: LLM Agents for Scalable Trading

Client Server; Greater London; On-site; GBP 120,000 - 150,000; Full time

Benefits offered by this job

Salary up to £150k

Benefits package

Job summary

Client Server is seeking an Applied AI Engineer to build production-grade AI systems that automate complex, document-heavy trading processes. You will design AI agents and LLM-powered applications, collaborating with data science, engineering and business teams to deliver reliable, scalable workflows.

The role focuses on testing, observability and robust deployment in a production environment, with a central London office and a typical Monday-to-Friday schedule.

Qualifications

• A 2.1 or above in a STEM discipline from an Oxbridge or Russell Group university.
• Strong Python engineering skills with production-grade AI applications.
• Hands-on experience developing LLM-powered applications and autonomous or semi-autonomous AI agents.
• Experience with document processing, RAG, tool calling, vector databases and agent memory.
• Strong knowledge of FastAPI, Pydantic, asynchronous Python and API development.
• Experience with PydanticAI or similar agent frameworks.
• Understanding of MCP, AI guardrails, evaluation frameworks and human-in-the-loop workflows.
• Experience building microservices and deploying applications using Docker, AWS and CI/CD.
• Strong testing and engineering practices to make AI systems robust, scalable and production-ready.

Skills

Python engineering

LLM powered apps

Autonomous AI agents

Document processing

RAG & vector databases

Tool calling & agent memory

FastAPI & Pydantic

Async Python & API dev

PydanticAI or agent frameworks

MCP, guardrails, human-in-the-loop

Microservices & CI/CD

Testing & engineering practices

Education

STEM degree (2.1+), Oxbridge or Russell Group

Tools

Docker

AWS

CI/CD tooling

Job description

Client Server is seeking an Applied AI Engineer to build production-grade AI systems that automate complex, document-heavy trading processes. You will design AI agents and LLM-powered applications, collaborating with data science, engineering and business teams to deliver reliable, scalable workflows.

The role focuses on testing, observability and robust deployment in a production environment, with a central London office and a typical Monday-to-Friday schedule.