Responsibilities
- Design and develop agentic AI systems capable of planning, reasoning, and executing tasks with minimal human input.
- Implement LLM-based agents using frameworks such as LangGraph, AutoGPT, CrewAI, AgentOps, or similar.
- Build and integrate Retrieval-Augmented Generation (RAG) pipelines to enable contextual grounding for agents.
- Fine-tune and prompt-engineer foundation models (OpenAI, LLaMA, Mistral, etc.) for domain-specific use cases.
- Collaborate with cross-functional teams to identify use cases and implement scalable AI solutions.
- Monitor agent performance, identify bottlenecks, and improve reliability and efficiency.
Requirements
- 5+ years of experience in Data Science, Machine Learning, or AI.
- Strong Python programming skills and familiarity with AI/ML frameworks (TensorFlow, PyTorch, HuggingFace).
- Hands-on experience with LLMs, prompt engineering, RAG, and vector databases (e.g., FAISS, Pinecone, Weaviate).
- Practical knowledge of agentic AI frameworks (Langraph, CrewAI, AutoGPT, etc.).
- Familiarity with orchestration tools like Airflow, FastAPI, or similar.
- Good understanding of RESTful APIs, microservices, and cloud platforms (AWS/GCP/Azure).
- Should have worked in the Healthcare insurance space from the payer side
Nice to Have
- Exposure to LangGraph, Semantic Kernel, or agent evaluation frameworks
- Experience working in domain-specific AI applications (e.g., healthcare, insurance, customer service).
- Demonstrated ability to iterate quickly on prototypes and scale them into production-grade components.
