Job Description

Design, develop, and deploy end-to-end AI-powered enterprise platforms by combining front-end and back-end engineering with advanced GenAI capabilities. Build intuitive user interfaces and scalable APIs that integrate Large Language Models (LLMs), enabling intelligent automation across insurance workflows such as underwriting, claims processing, and loss run extraction. Develop and optimize prompts, orchestration logic, and agentic AI workflows to drive high-accuracy decisioning. Leverage strong Machine Learning and Deep Learning foundations to architect robust, secure, and production-ready systems, ensuring scalability, reliability, and seamless user experience across AI-driven applications.

Roles & Responsibilities:

• Act as SME for prompt engineering and AI solutions, defining standards, reusable templates, and guardrails for insurance workflows.
• Design, test, and optimize prompts for document extraction, claims summarization, fraud signals, and underwriting decision support.
• Build React-based UX for document intake, AI copilots, explainability, and human-in-loop review workflows.
• Develop secure, scalable ASP.NET Core APIs to expose AI services, orchestrate workflows, and integrate enterprise systems.
• Orchestrate agentic AI workflows with multi-step reasoning, tool calling, retries, and audit-ready traceability.
• Implement RAG architectures for grounded insights using vector search, contextual retrieval, and citation-backed responses.
• Apply ML/DL techniques (classification, clustering, embeddings, sequence models) to enhance LLM accuracy and routing.
• Integrate traditional ML/NLP models with LLM pipelines to deliver hybrid, production-grade AI solutions.
• Collaborate with underwriting, claims, and actuarial stakeholders to translate business needs into deployable AI features.
• Drive architecture decisions for scalable, resilient, and cost-optimized AI platforms with multi-tenant support.
• Implement evaluation frameworks covering precision, recall, hallucination detection, and grounding metrics with CI gates.
• Continuously optimize systems for accuracy, consistency, latency, and cost using telemetry, caching, and model routing.
• Establish CI/CD pipelines, automated testing, observability, and secure coding practices for enterprise AI delivery.
• Mentor teams on GenAI best practices, prompt engineering, ML fundamentals, and full-stack (.NET + React) development.

Technical Stack:

1. Strong experience in API development and microservices architecture using ASP.NET Core (.NET) with secure, scalable service design.
2. Expertise in building front-end applications using React, enabling AI-driven UX such as copilots, document review, and explainability interfaces.
3. Ability to design and integrate end-to-end AI systems across React front-end, .NET back-end, and Python-based AI/ML services in a distributed architecture.
4. Proficiency in NLP/GenAI frameworks and libraries for building AI pipelines using Python (As required)
5. Hands-on experience with OpenAI APIs/LLM platforms, LangChain/LangGraph, and vector databases (Pinecone, FAISS) for RAG and agentic workflows.
6. Working knowledge of ML/DL frameworks (TensorFlow/PyTorch) to support model tuning, embeddings, and advanced analytics.