Description

You will design, fine-tune, and deploy Large Language Models (LLMs) for insurance-specific use cases, including document intelligence and claims summarization.

This role is on-site.

Responsibilities

• Build Retrieval-Augmented Generation (RAG) pipelines using vector databases like ChromaDB and Azure AI Search to ground LLM outputs in enterprise knowledge.
• Architect autonomous AI agents for multi-step reasoning and decision-making, implementing patterns such as ReAct and Chain-of-Thought.
• Build and maintain end-to-end MLOps pipelines for model training, versioning, and deployment using MLflow and Azure ML.
• Implement CI/CD pipelines for ML models using Azure DevOps or GitHub Actions and deploy models as REST APIs on Azure Kubernetes Service.
• Collaborate with business analysts and underwriters to translate domain requirements into AI solution designs and produce technical documentation.

Required Skills

• 3–5 years of professional experience in AI/ML engineering with production-grade AI system delivery.
• Hands-on experience building LLM-powered applications using LangChain, LlamaIndex, or Semantic Kernel.
• Proven experience implementing MLOps pipelines in cloud environments, specifically Azure ML.
• Experience developing AI agents or automation workflows using agentic frameworks.
• Proficiency with vector databases such as ChromaDB, Pinecone, or Azure AI Search.
• Experience with orchestration tools like Azure Logic Apps, Apache Airflow, or Databricks Workflows.
• Ability to deploy models as REST APIs or batch inference services.

Preferred Skills

• Prior experience in financial services, insurance, or regulated industries.

Key Skills

Education

Any Gradute