AI engineer in agentic systems

I'm working on an exciting opportunity for three Senior AI Engineers to join a growing AI and data consultancy, building production-grade AI systems using cutting-edge agentic technology. This is an opportunity for engineers who have moved beyond AI experimentation and have real-world experience building, deploying and scaling multi-agent AI systems in production. The mission is to take an existing Claude-based multi-agent AI solution and transform it into a reliable, scalable and production-ready platform.

• Designing and building multi-agent AI architectures using Claude.
• Developing production-grade AI workflows using Python.
• Building agent orchestration, parallel processing and verification mechanisms.
• Improving LLM reliability through evaluation, testing and error handling.
• Optimising token usage, execution costs and latency.
• Working with PostgreSQL, Azure Data Lake Storage and modern data technologies.
• Implementing CI/CD, automated testing, monitoring and production deployment.
• Making architectural decisions that directly influence the platform's future.

• Strong hands-on Python engineering experience.
• Proven experience building and deploying multi-agent AI systems into production.
• Experience with Claude, the Claude Agent SDK or Claude Code.
• A solid understanding of LLM evaluation, agent orchestration and AI reliability.
• Experience with Git, CI/CD, automated testing and Docker.
• Familiarity with PostgreSQL and Azure-based data platforms.
• The ability to discuss systems you've built, challenges you've faced and how you've solved them.

Experience with in pharmaceutical or other regulated environments would be advantageous, but the priority is genuine production-grade AI engineering expertise

Initial 6 months, with a likelihood of extension. Mostly remote, with occasional travel to London as required.