Description

Develop and evaluate LLM-powered agents and agentic workflows for natural language understanding and retrieval tasks.

This role is on-site.

Responsibilities

• Build and iterate on LLM agents for task execution, reasoning, and retrieval across structured and unstructured data.
• Own model evaluation and validation pipelines for LLM and RAG workflows, including performance tracking and ablation studies.
• Collaborate with product managers and engineers to integrate intelligent systems into customer-facing platforms.
• Write production-grade Python code and contribute to reusable components and pipelines.
• Apply analytical problem-solving to define rules and optimize agent behaviors.

Required Skills

• 5+ years of experience in applied AI or PhD-level research.
• Strong programming proficiency in Python for scalable ML/AI applications.
• Hands-on experience with LLMs, including prompt engineering, fine-tuning, or agentic architectures (LangGraph, AutoGen, CrewAI).
• Expertise in model evaluation for LLM systems, including designing metrics and running A/B tests.
• Experience with Vector Databases (e.g., FAISS, Pinecone) and LLM frameworks (LangChain).
• Familiarity with cloud platforms, specifically GCP.
• Experience with Git and VS Code.

Preferred Skills

• PhD-level research experience in AI.
• Experience integrating agents into associate-facing platforms.

Key Skills

Education

Any Graduate