Lead AI Research Engineer – Agentic Systems
New York (hybrid)
The following information provides an overview of the skills, qualities, and qualifications needed for this role.
Our client, a global information and technology company, is hiring a Lead AI Research Engineer for its applied AI research group. The team builds AI products used by professionals in law, tax, compliance and government around the world. These are high-stakes domains where accuracy and trust matter.
The role
You’ll lead the technical design and delivery of production agentic AI systems, taking each one from an unclear business problem to a system customers can rely on. You’ll set engineering standards, mentor other engineers and work closely with research scientists to turn new ideas into products.
What you’ll do
- Design, build and optimise multi-agent systems for production, including complex tool calling, context management and workflow orchestration
- Build evaluation frameworks that go beyond offline metrics to measure how agents actually perform in live systems
- Own agent observability and telemetry
- Lead engagement across Product, UX, Engineering and Business stakeholders
- Set best practices and standards that scale, and raise the technical bar through mentorship
- Build scalable data pipelines and ML systems across the full software lifecycle
What you’ll bring
- 8+ years of hands-on engineering experience building IR, NLP, LLM or agentic systems for commercial products in production (not academic or experimental work)
- Deep expertise in agentic AI: tool use, multi-agent orchestration, context management and agent evaluation
- Expert-level production Python: clean, tested, maintainable code. Pydantic/PydanticAI experience is a strong plus
- Familiarity with PyTorch and Hugging Face, and a solid grasp of ML fundamentals
- Experience with LLM observability/eval platforms such as Langfuse or xhqgsiq Braintrust
- Cloud-native and MLOps experience (AWS or Azure)
- A track record of leading technical workstreams and influencing cross-functional stakeholders
- Daily use of AI-assisted coding tools such as Cursor or Claude Code
- Nice to have: NER, information extraction or retrieval experience; Java/TypeScript
What’s on offer
- Competitive salary and benefits
- Hybrid working, plus up to 8 weeks a year working from anywhere
- Flexible vacation, wellbeing support and tuition reimbursement
- Work on AI products used by millions of professionals worldwide
Research Engineer in new york at Unknown Company
This position is listed as full time and hybrid.