Data Engineer III

Join a dynamic, high-performing team where your distinctive skills will contribute to a winning culture and strong outcomes. 

As a Software Engineer III at JPMorgan Chase within Consumer & Community Banking   ,you will be a seasoned member of an agile team designing and delivering end-to-end application development across both frontend and backend components, while leveraging agentic AI capabilities to deliver business solutions in scalable way. You will develop, test, and maintain critical end to end application, application data and architectures, and you'll partner across business and technology teams to support the firm's objectives.

This role is ideal for someone who is dynamic and hands-on, with the ability to use agentic tools efficiently to accelerate delivery across full-stack development, data engineering, and machine learning enablement.

Job Responsibilities

• Design and build ML systems end-to-end: problem framing, data prep, feature engineering, model training, evaluation, deployment, monitoring, and iteration.
• Develop agentic AI solutions: LLM agents that plan, call tools/APIs, run multi-step workflows, and apply guardrails/fail-safes.
• Implement RAG capabilities: retrieval strategy, chunking, embeddings, indexing, and re-ranking to ground agent responses in knowledge.
• Build full-stack product experiences for ML/agent systems: backend services plus frontend UIs for configuration, human-in-the-loop review, observability, and workflow execution.
• Develop and integrate APIs/services: design and implement RESTful (and/or event-driven) integrations to serve models, agents, features, and data products.
• Build scalable data pipelines with Apache Spark (PySpark/Scala) for batch processing and feature generation.
• Use SQL extensively for exploration, transformations, validation checks, and query performance tuning on large datasets.
• Operationalize and evaluate ML/LLM systems with MLOps: CI/CD, model registry, experiment tracking, reproducible training, automated evaluation/regression tests, and quality frameworks (offline metrics + HITL).
• Leverages enterprise-authorized AI coding assist tools within the work environment to improve code quality, delivery speed, and productivity across complex deliverables (e.g., code generation/refactoring, unit test creation, documentation), while validating outputs through peer review, automated testing, and secure coding standards; contributes learnings and reusable patterns to improve broader team effectiveness.
• 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, skills, and capabilities

• 3+ years delivering production ML solutions, owning the end-to-end lifecycle from problem framing through deployment and iteration.
  Experience in React, octagon framework for UI development.
  Experience in building , integrating APIs for Experience services.
• Strong ML fundamentals, including supervised/unsupervised learning, feature engineering, model evaluation, bias/variance tradeoffs, and error analysis.
• Hands-on agentic AI / LLM application development, including tool/function calling, planning, and memory patterns.
• Experience building RAG pipelines, covering retrieval strategies, chunking, embeddings, and re-ranking approaches.
• Implemented LLM guardrails, such as policy checks, refusal handling, PII filtering, and deterministic fallback behaviors.
• Strong Python programming skills for building ML/LLM systems and supporting tooling.
• Full-stack engineering experience, building/operating backend APIs/services (REST and/or event-driven) and modern web frontends (React/Angular/Vue) for HITL workflows, configuration, and monitoring/analytics.
• Advanced data engineering/query skills, including expert SQL (joins, window functions, CTEs, optimization), strong Apache Spark/PySpark (DataFrames, Spark SQL, tuning/partitioning), and experience running ML services with monitoring and alerting (batch or real-time).
• 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