AI Engineer

Position Overview As an AI Engineer at Prescient, you will build and deploy GenAI / agentic AI systems that power our competitive intelligence products in the pharmaceutical and life sciences space. Your role involves developing LLM agents that query external data sources, creating retrieval pipelines over specialized content, implementing evaluation frameworks, and building APIs and dashboards that deliver insights to analysts and clients. You will work in a fast-paced environment with tight feedback loops, real users, and short release cycles, directly contributing to Prescient's technology-driven competitive advantage in the life sciences consulting sector. Example Responsibilities Design and implement agentic AI systems that query external data sources and process pharmaceutical and biotech information Develop robust retrieval pipelines over specialized life sciences content to extract valuable competitive intelligence Create and maintain evaluation harnesses to ensure accuracy, reliability, and ethical operation of AI systems Engineer production-grade prompts and structured-output parsing mechanisms for consistent AI performance Build and optimize RAG (Retrieval-Augmented Generation) stacks to enhance knowledge retrieval from domain-specific content Develop REST APIs using FastAPI or similar frameworks to integrate AI capabilities into Prescient's product ecosystem Design and implement dashboards that effectively communicate AI-generated insights to analysts and clients Collaborate with data scientists and domain experts to continuously improve AI system performance and relevance Write clean, typed, and well-tested Python code following best practices for maintainability and scalability Troubleshoot complex issues in multi-turn agent interactions and implement robust error handling mechanisms Education, Experience, Knowledge & Other Skills Required 3–4 years experience writing production Python, including async, typed and tested code Experience shipping an agentic system involving tool calling, multi-turn state and failure handling Experience building or maintaining an evaluation set for LLM output Production prompt engineering and structured-output parsing expertise Experience building one RAG stack end to end REST API development using FastAPI or similar frameworks Relational database fundamentals and ability to write non-trivial SQL queries Tech, M.Tech, MCA, or equivalent education Preferred Agent harness engineering, including execution environments, sandboxing, permissions, context management, retries, interrupts and sub-agent spawning Agent control-loop design, including self-verification, stopping criteria, turn limits and recoverable error handling Experience with LangGraph, Strands, MCP or AWS Bedrock AgentCore Familiarity with Braintrust, LangSmith, Promptfoo, DeepEval or equivalent evaluation tooling Life sciences or pharma data exposure Front-end development for internal tools using HTML, JavaScript, charting libraries or React Experience with Docker, ECS or Kubernetes What We Offer Opportunity to work on cutting-edge AI systems with direct impact on pharmaceutical and life sciences decision-making Collaborative environment with a team of technology and domain experts Clear career progression path with mentorship from senior technical leaders Professional development opportunities including training, and certifications Competitive compensation package with comprehensive benefits Flexible hybrid working arrangement at our Gurugram office