🎁 Before you apply, rehearse this interview. Create your free WorkMundi account and get an Interview Training on HelpsYouSpeak — no cost, no card. I want my training →
Roles & Responsibility: Own the end-to-end architecture and technical direction for production-grade GenAI solutions including RAG, LLM applications, agents, and multi-agent workflows. Lead hands-on development from POC to production, ensuring scalable, reliable, and maintainable GenAI solutions that serve real users. Design and optimize RAG pipelines, AI agents, function calling, MCP-based workflows, and LLM-powered products for complex healthcare use cases. Establish LLM evaluation frameworks, hallucination guardrails, accuracy benchmarks, observability, and responsible-AI practices suitable for regulated healthcare data. Drive improvements in model performance, latency, scalability, inference efficiency, and LLM/API costs across production workloads. Lead a small engineering pod, provide technical mentorship, conduct code/design reviews, and establish engineering best practices across GenAI development. Own GenAI deployment and operationalization using Python, cloud platforms, Docker, CI/CD, monitoring, and MLOps practices, while collaborating with product and engineering stakeholders .