Lead Software Engineer - AI

Lead Software Engineer – Agentic Systems

I’m working with a global technology organisation looking for a Lead Research Engineer to help build the next generation of production AI systems.

This is not an academic or experimental AI role. You’ll be taking complex AI concepts from ambiguity through to reliable, customer-facing systems — with a particular focus on LLMs, agentic AI, NLP, information retrieval and production engineering.

What you’ll be doing

• Designing and building production-grade agentic AI systems, including tool use, multi-agent orchestration and complex workflows
• Owning context management, agent observability and telemetry, with platforms such as Langfuse and Braintrust relevant to the environment
• Building and optimising scalable AI/ML systems in production Python
• Developing comprehensive evaluation frameworks that measure not just offline model performance, but the real-world quality of agents in live systems
• Working across LLMs, NLP, Information Retrieval and ML, turning emerging technology into practical customer applications
• Setting engineering standards and best practices across AI initiatives
• Partnering closely with Product, UX, Technology and Business stakeholders to take ideas from problem definition through to delivery
• Mentoring engineers and acting as a technical force multiplier across the wider organisation
• Using modern AI-assisted development tools such as Cursor and Claude Code to accelerate engineering productivity

What they’re looking for

• 7+ years of hands-on commercial experience building IR, NLP, LLM or agentic systems
• Strong track record taking AI systems from prototype to production
• Expert-level Python, with a focus on clean, maintainable and well-tested code
• Strong experience with Pydantic / PydanticAI, with familiarity across PyTorch and Hugging Face
• Deep understanding of multi-agent architectures, tool calling, orchestration and context management
• Experience designing end-to-end AI evaluation and observability frameworks
• Strong software engineering fundamentals across system design, scalability, testing, monitoring and cloud-native development
• Experience with AWS
• Background in NLP / Information Retrieval, including areas such as NER, information extraction, search or ranking
• Experience working alongside research scientists to productionise research
• The ability to lead technical initiatives while influencing stakeholders across Product, UX and Business
• A genuine interest in using AI-assisted coding tools to improve how you build software

It’s a high-impact technical leadership role for someone who wants to sit at the intersection of AI research, agentic systems and serious production engineering.

If you’re building production agentic systems today and want to influence how AI is engineered at enterprise scale, I’d be keen to speak.

This role can be hired out of New York, Toronto, Zug, London, Frisco, Ann Arbor, & St Paul's.