Build Halt
AI Engineer (Mid–Senior)
Get notified of more jobs like this · No spam, ever
How your CV stacks up
Upload your CV to see how well it fits this job role
?%
Senior AI Engineer: Production AI Agents
We're looking for a Senior AI Engineer. You'll take a rough idea, turn it into a working prototype, and ship it as a reliable, monitored system that real users depend on every day. You'll design it, build it, ship it and make it better over time.
What you'll do
- Take full ownership of AI agent products from start to finish: scoping, architecture, build, deployment and ongoing improvement
- Design and build agentic systems that use tools, call APIs, carry out multi-step tasks and hold up under real-world messiness
- Turn prototypes into production systems with proper error handling, fallbacks, guardrails and human-in-the-loop where it matters
- Build evaluation frameworks and test suites so we know an agent works before it ships, not after
- Set up observability for agent behaviour (tracing, logging, cost and latency monitoring) and act on what it shows
- Integrate LLMs (Claude, GPT and open-source models) with internal systems, data sources and third-party tools, including via MCP
- Set engineering standards for AI work and collaborate within an adaptable fast pace environment
Reasons to use Rodeo
Start with a chat, not a search bar
Grad scheme, placement, apprenticeship? Not sure what you want yet — that's fine. Your agent talks it through with you and turns "I have no idea" into a shortlist.
It searches the market for you
Every day your agent scans the market matching roles against what actually matters to you, not just keywords on a CV.
Only hits
No noise. No "maybe this fits." Just roles with a clear explanation of why they're right — and where to focus when applying.
What you'll bring
- 5+ years in software engineering
- A track record of shipping AI agents or LLM systems to production. We'll want to hear the war stories
- Strong Python and/or TypeScript skills
- Hands-on experience with tool use and function calling, multi-step agent orchestration, RAG and prompt engineering
- A solid grasp of how LLM systems fail (hallucination, drift, prompt injection, runaway costs) and how to design around it
- Experience with evals, testing and monitoring for non-deterministic systems
- Cloud and deployment experience (AWS / GCP / Azure, containers, CI/CD)
- Product instinct: you care whether something is useful, not just whether it's clever
- Comfort working with ambiguity and owning outcomes end-to-end
Get help with your application
Your very own career expert that helps elevate your application to the next level.
Nice to have
- Experience with agent frameworks (e.g. LangGraph, Claude Agent SDK, OpenAI Agents SDK) and knowing when not to use one
- MCP server development
- Vector databases and retrieval optimisation
- Security experience with AI systems (sandboxing, permissions, injection defence)
- Experience in a startup or consultancy environment
Why join us
- Real ownership: your agents, your architecture, your impact
- Work on production AI, not endless proofs of concept
- Salary negotiable
- On site setup, holiday allowance, learning budget, other benefits
- A small, senior team where your work is visible and matters
Interested? Apply below or message me directly. Bonus points if you tell us about an agent you've taken all the way to production: what broke, and how you fixed it.
“It took my CV and asked me questions relevant to understanding what kind of jobs to suggest for me. Suggestions were almost perfect. Jobs were exactly what I’ve been looking for.”
Jessica, London
Location