• Stay up to date with the state-of-the-art in Artificial Intelligence and Machine Learning. • Make use of techniques such as In-Context Learning and Tool Calling. • Work in an “eval-driven development” methodology. • Collaborate with cross-functional teams to ship and iterate on production-grade AI products. • Own the end-to-end development of AI features of a customer-facing product.

• Stay up to date with the state-of-the-art in Artificial Intelligence and Machine Learning, and apply it to the problem of Enterprise Vibe Coding; • Make use of techniques such as In-Context Learning (Prompt Engineering & Retrieval Augmented Generation) and Tool Calling to guide Agents to perform as intended; • Work in an “eval-driven development” methodology, applying evaluation techniques such as model-based critiques, semantic accuracy benchmarks, and tool-use success rates as the basis for developing robust, reliable, and production-ready LLM Agents; • Work across the entire lifecycle of product development, from ideation, through prototyping and designing to implementation and evaluation; • Collaborate with cross-functional teams to ship and iterate on production-grade AI products; • Own the end-to-end development of AI features of a customer-facing product, ensuring software quality, observability and scalability; • Be a thought leader in the space, advancing the field by putting the most forward ideas into practice in a large-scale project.

• Manage and mentor a team of data engineers, ML engineers, and knowledge engineers in India. • Coordinate delivery with US-based technical leadership across time zones. • Drive hiring and onboarding as the India team scales. • Own sprint planning, delivery cadence, and progress reporting. • Ensure technical quality through code reviews, architecture discussions, and engineering standards. • Collaborate with the Principal Architect and ML Engineering Lead on technical direction. • Remove blockers, manage cross-team dependencies, and ensure smooth collaboration. • Contribute to data architecture and pipeline design decisions.

• Design and implement AI-powered features: integrate LLM and build AI agents. • Design and implement end-to-end (frontend and backend) non-AI features, services and business logic that make the solution complete. • Build and maintain MCP servers to expose domain data and capabilities as tools for AI agents. • Implement RAG workflows to ground LLM responses in factual data using embeddings, chunking and vector databases. • Instrument and optimize OpenAI integrations for cost, latency, and accuracy in production environments. • Collaborate with product, design and architecture teams to craft exceptional user experiences built on AI. • Participate in technical design reviews, shaping architectural decisions and engineering standards.