Role: Engineering Lead - Intelligence Platform

Experience: 10+yrs Position Overview

We are seeking an exceptionally talented and highly operational Engineering Lead to spearhead the Intelligence Platform that powers our AI-native insurance core. You will lead hands-on, by example, architecting and building the foundational capabilities that enable AI-assisted, Hybrid, and Autonomous insurance operations. You will work across agent orchestration, advanced RAG, context management, decision intelligence, explainability, governance, and AI observability.

The ideal candidate has successfully navigated the industry shift from traditional software and machine learning systems to Foundation Models, Agentic AI, and modern AI engineering. You have a robust engineering background, experience building production-grade AI systems, and the ability to convert emerging AI capabilities into reliable enterprise software.

Your mission is to build the Intelligence Platform that enables insurers to progressively hand more work to the system while maintaining governance, accountability, explainability, and control.

Key Responsibilities

Build the Intelligence Platform: Design and evolve the foundational intelligence layer that powers OneBuzz. This platform will enable AI-assisted, Hybrid, and Autonomous insurance operations by providing the core capabilities for orchestration, reasoning, governance, explainability, and execution across underwriting, policy administration, servicing, and claims.

Operational & Architectural Leadership: Architect, code & deploy the intelligence platform. Own technical delivery of Agent orchestration frameworks, context & memory systems, Decision intelligence services, Human-in-the-loop workflow, AI observality and evaluation capabilities

Context, RAG & Decision Intelligence: Build the systems that allow AI to reason using business context rather than isolated prompts. Develop advanced retrieval, knowledge,



and decision intelligence capabilities that make every AI-assisted action contextual, reproducible, explainable, and auditable.

Evaluation & LLMOps: Establish rigorous evaluation, observability, and governance frameworks for production AI systems. Build automated benchmarking and monitoring capabilities to continuously measure accuracy, reasoning quality, hallucination rates, latency, cost-efficiency, model drift, and token optimization before every production release.

Required Experience & Qualifications

10+ years of engineering experience

3+ years building AI-native or LLM-powered systems

Proven track record of shipping production AI systems

Experience leading architecture and technical delivery

Experience within insurance, financial services, healthcare, fintech, or other regulated industries is highly desirable.

Technical Stack Expertise

Deep expertise in LLMs, Agentic AI, Tool Calling, Function execution

Hands-on experience with LangGraph, LangChain, MCP, Vercel AI SDK, Custom Agent Framework

Strong understanding of Vector databases, Advanced RAG architecture, Embeddings, Knowledge graphs, Context retrieval strategies

Experience with Langfuse, Langsmith or similar tools for tracing, evaluation, observability, and benchmarking AI systems

Soft Skills & Mindset

Product-Minded & Business-Driven : You care about user impact, business outcomes, operational adoption, and practical value creation—not just building AI models.

High Ownership

- You thrive in lean, high-performing environments and enjoy building new platform capabilities from first principles.

Systems Thinker

- You think beyond individual AI use cases and focus on reusable platform capabilities that scale across products, business functions, and geographies.

Communication

- Exceptional ability to explain AI systems, architectural trade-offs, and technical concepts to Product Managers, Architects, Domain Experts, Executives, and Customers

📌 Engineering Lead (Gurugram)
🏢 Eicore
📍 Gurugram