Description

You will lead the development of agentic AI solutions, owning the architecture and implementation of LLM-based systems.

This role is on-site.

Responsibilities

• Build and enhance LLM/agent orchestration, including planner/supervisor patterns, tool-using agents, routing, and guardrails.
• Implement intent classification, information extraction, validation, and decision logic for servicing workflows.
• Design and implement retrieval-augmented generation (RAG) for policy grounding and resolution guidance.
• Define and run evaluation frameworks using golden datasets, scenario tests, and automated scoring.
• Implement observability for agents, tracking latency, cost, tool failures, drift, and quality signals.

Required Skills

• 8+ years of software engineering experience with strong CS fundamentals.
• Deep experience in Agentic AI Development, building with LLMs and the modern AI stack (agents, RAG, tool/function calling).
• Strong proficiency in Python for building back-end services and APIs.
• Experience with LangChain/LangGraph, LlamaIndex, Semantic Kernel, or equivalent frameworks.
• Experience with vector databases and search (e.g., Pinecone, Weaviate, Milvus, OpenSearch/Elastic).
• Experience deploying services in cloud environments (AWS/Azure/GCP) with basic DevOps practices.
• Strong understanding of security and privacy principles, including PII handling and audit logging.
• Hands-on experience building knowledge ingestion pipelines with refresh and versioning.

Key Skills

Education

Bachelor's degree