Associate - Data Science / Applied AI ML

JPMorgan Chase JPMorgan Chase · Banking · Bengaluru, Karnataka, India · Corporate Sector

This role focuses on building and enhancing AI agents and applications, specifically leveraging LLMs, Generative AI, and Agentic AI. The responsibilities include developing orchestration workflows, integrating with enterprise systems via MCP, and implementing RAG/GraphRAG solutions. The role requires strong Python and SQL skills, experience with LLM platforms and prompt engineering, and a solid understanding of agentic AI concepts like tool calling and multi-step reasoning. Experience with enterprise integration patterns and RAG/vector database technologies is also key. The role is within JPMorgan Chase, a financial services company, indicating a regulated environment.

What you'd actually do

  1. Develop AI-powered applications leveraging LLMs, Generative AI, Agentic AI, and advanced analytics.
  2. Build and enhance AI agents that interact with enterprise tools, data sources, APIs, and business workflows.
  3. Develop orchestration workflows using frameworks such as LangGraph, Semantic Kernel, LangChain, or similar technologies.
  4. Implement MCP (Model Context Protocol) integrations to securely connect AI applications with enterprise systems, knowledge sources, and services.
  5. Build and support Retrieval-Augmented Generation (RAG), GraphRAG, and Knowledge Graph solutions.

Skills

Required

  • Python
  • SQL
  • LLMs
  • Generative AI platforms
  • prompt engineering
  • AI application development
  • orchestration frameworks
  • LangGraph
  • LangChain
  • Agentic AI concepts
  • tool calling
  • workflow automation
  • memory management
  • multi-step reasoning
  • MCP (Model Context Protocol) integrations
  • enterprise integration patterns
  • RAG
  • embeddings
  • vector databases
  • semantic search
  • knowledge retrieval techniques
  • REST APIs
  • JSON
  • enterprise system integrations

Nice to have

  • Neo4j
  • Knowledge Graphs
  • GraphRAG architectures
  • AI observability
  • evaluation frameworks
  • LLM testing methodologies
  • cloud-based AI platforms
  • enterprise AI ecosystems
  • compliance
  • risk management
  • financial services domains
  • AI copilots
  • assistants
  • multi-agent systems

What the JD emphasized

  • Agentic AI
  • orchestration workflows
  • LangGraph
  • LangChain
  • MCP (Model Context Protocol)
  • RAG
  • GraphRAG
  • Knowledge Graph

Other signals

  • Develop AI-powered applications leveraging LLMs, Generative AI, Agentic AI
  • Build and enhance AI agents that interact with enterprise tools, data sources, APIs, and business workflows
  • Develop orchestration workflows using frameworks such as LangGraph, Semantic Kernel, LangChain, or similar technologies
  • Implement MCP (Model Context Protocol) integrations to securely connect AI applications with enterprise systems
  • Build and support Retrieval-Augmented Generation (RAG), GraphRAG, and Knowledge Graph solutions