Context Plane Python Engineer

Join a greenfield engineering effort at the heart of JPMorganChase's AI strategy. As part of the Corporate Technology Data and Analytics Services organization, you'll help build a platform that is redefining how AI agents and large language model tools access governed, trusted firm knowledge. This is a rare opportunity to shape architecture from the ground up, work alongside a small, senior team, and grow your expertise at the intersection of data engineering and applied AI — with full support to learn the graph and AI stack on the job.

As a Lead Software Engineer at JPMorganChase within the Data Core Engineering group, you will design and build the Context Plane — a platform that connects the data mesh and other knowledge sources to the AI agents and tools that consume firm context. You will own components end-to-end, from ingestion pipelines that load firm knowledge into graph and vector stores, to the serving layer that retrieves and returns governed, provenance-tagged context to downstream agents. Because this platform is early-stage, your engineering decisions will have lasting impact on how it evolves.

Job responsibilities

• Design, build, and maintain backend services and data pipelines in Python that load firm knowledge into a knowledge graph and vector store, ensuring reliability, security, and scalability
• Build and evolve the serving layer — including graph and vector retrieval, GraphRAG, response assembly, and a Model Context Protocol endpoint that agents call for context
• Extract and promote reusable components into a shared core library, reducing duplication and improving consistency across the platform's repositories
• Integrate with data sources and services across the firm, including AI and large language model gateways, to enable governed and traceable context delivery
• Own quality across your components through automated testing, code reviews, observability instrumentation, and resilient service design
• Partner with Corporate Technology AI, product, and data science colleagues to translate concrete use cases into working, measurable platform capabilities
• Contribute to design discussions and agile ceremonies, bringing pragmatic engineering instincts and a bias toward practical, scalable solutions
• Drives team adoption of enterprise-authorized AI-assisted engineering practices within the work environment to improve code quality, delivery speed, and operational outcomes (e.g., AI-assisted code review/refactoring, test strategy acceleration, incident/root-cause analysis support), while establishing consistent validation standards (secure coding, peer review, automated testing) and promoting reuse of effective patterns across the team
• Applies knowledge of tools within the Software Development Life Cycle toolchain, including enterprise-authorized AI-assisted development and automation capabilities, to improve the value realized by automation

Required qualifications, capabilities, and skills

• Formal training or certification on software engineering concepts and advanced applied experience
• Demonstrated proficiency in Python, with hands-on experience building production-grade backend services and data pipelines
• Strong grasp of API design principles (e.g., FastAPI or equivalent frameworks), automated testing, CI/CD practices, and source control workflows
• Experience building and operating containerized services on cloud infrastructure (e.g., AWS, Docker, ECS)
• Ability to own components end-to-end — from design through deployment and observability — with a pragmatic, outcome-focused engineering approach
• Demonstrated ability to collaborate cross-functionally with product, data science, and platform engineering teams to deliver working capabilities
• Hands-on experience using enterprise-authorized AI-assisted software development tools within the work environment (e.g., for coding, test creation, troubleshooting, or documentation) with demonstrated ability to critically evaluate, validate, and refine AI-generated outputs for correctness, performance, and security
• Understanding of responsible AI use in engineering workflows, including data sensitivity considerations, secure handling of inputs/outputs, and adherence to resiliency and security expectations; ability to guide peers on safe and effective usage within team practices

Preferred qualifications, capabilities, and skills

• Experience with graph databases and query languages (e.g., Neo4j, Cypher), or a strong interest in graph data modeling and knowledge graph design
• Familiarity with vector search, embeddings, or retrieval-augmented generation (RAG) patterns
• Exposure to large language model serving platforms (e.g., Bedrock, Azure OpenAI) or agentic patterns such as tool/function calling and Model Context Protocol
• Experience with Databricks, MongoDB, or large-scale data integration and ETL workflows
• Knowledge of data governance, data lineage, and entitlements concepts in an enterprise data environment