• Design and curate upper-undergraduate and graduate-level Biology problems with clear, fully worked solutions. • Create challenging, realistic tasks that expose failure modes in frontier AI systems. • Convert diagram-heavy or multi-part biology questions into self-contained, text-only problems with definitive answers. • Write rigorous explanations and verify scientific accuracy throughout the problem and solution. • Evaluate AI-generated responses, diagnose errors, and refine questions to meet difficulty targets. • Review Biology tasks created by others and improve clarity, correctness, and realism. • Collaborate with cross-functional teams to maintain consistent standards across large task batches.

• Design and solve challenging Maths problems to probe the limitations of large language models. • Create clear, high-quality, step-by-step solutions with well-articulated reasoning. • Collaborate with LLM researchers to align problems with evaluation goals, especially in areas where models struggle (e.g., abstraction, multi-step reasoning, symbolic manipulation). • Help define new evaluation benchmarks based on Mathematics curricula spanning early undergraduate to PhD-level topics.

• Lead a team of AI Engineers, ensuring alignment on goals, quality and delivery timelines. • Mentor and coach team members to support their technical and professional growth. • Drive engineering excellence by promoting best practices in coding (PEP-8, Clean Code), Test-Driven Development, code review, CI/CD and responsible AI development. • Plan and manage team capacity, sprints and milestones to ensure predictable delivery. • Own the design, evolution and operation of our RAG and agentic AI services — retrieval, embedding, indexing, orchestration, evaluation and LLM Ops. • Set and maintain standards for prompt engineering, evaluation harnesses, guardrails, hallucination mitigation and content safety. • Partner with the Data team to expose curated Druid datasets through natural-language interfaces (text-to-SQL / semantic search) and ensure quality and consistency end-to-end. • Collaborate with Product, UX and Architecture to translate customer and internal use cases into well-defined AI capabilities with clear acceptance criteria. • Champion responsible AI — bias awareness, transparency, privacy, data minimisation, evaluation, monitoring, and clear in-product communication of model limitations. • Collaborate with other Team Leaders, Development Managers, Architects and Product Owners to align engineering execution with business objectives. • Contribute to the evolution of development processes, CI/CD pipelines and DevOps practices. • Foster a culture of continuous improvement, innovation and knowledge sharing — including a research-aware approach to a fast-moving field.

• Own outcomes end-to-end — not tasks, not tickets. You pick a problem, architect the AI-powered solution, ship it, and measure the impact yourself. • Build agentic systems — design autonomous loops that reason, act, and iterate. Think agents that handle workflows, not just answer questions. • Deploy autonomous pipelines end-to-end — no human in the middle. From trigger to result, your systems handle the reasoning, the actions, and the handoffs. You measure output, not effort. • Operate as a one-person company — scope, prioritize, execute, and iterate with radical ownership. AI is your team. • Cross-pollinate across CloudWalk — what you build in your domain becomes a blueprint for every other team.