Description

You will design and develop agentic AI systems that plan, reason, and execute tasks with minimal human input.

Responsibilities

• Implement LLM-based agents using frameworks like LangGraph, CrewAI, or AutoGPT.
• Build and integrate Retrieval-Augmented Generation (RAG) pipelines for contextual grounding.
• Fine-tune and prompt-engineer foundation models (OpenAI, LLaMA, Mistral) for domain-specific use cases.
• Monitor agent performance to identify bottlenecks and improve reliability and efficiency.
• Collaborate with cross-functional teams to implement scalable AI solutions.

Required Skills

• 5+ years of experience in Data Science, Machine Learning, or AI.
• Strong Python programming skills with familiarity in TensorFlow, PyTorch, and HuggingFace.
• Hands-on experience with LLMs, prompt engineering, RAG, and vector databases (FAISS, Pinecone, Weaviate).
• Practical knowledge of agentic AI frameworks (LangGraph, CrewAI, AutoGPT).
• Familiarity with orchestration tools like Airflow and FastAPI.
• Understanding of RESTful APIs, microservices, and cloud platforms (AWS, GCP, Azure).
• Experience in the Healthcare insurance space from the payer side.

Preferred Skills

• Exposure to Semantic Kernel or agent evaluation frameworks.
• Ability to iterate quickly on prototypes and scale them into production-grade components.

Key Skills

Education

Bachelor's degree