Lead Software Engineer - Java and Ai/ml

JPMorgan Chase JPMorgan Chase · Banking · Mumbai, Maharashtra, India · Commercial & Investment Bank

Lead Software Engineer focused on building AI agents and integrating AI/ML tools into engineering workflows, primarily using Java and Spring Boot, with some Python for prototyping. The role involves developing secure, scalable microservices and APIs, and driving team adoption of AI-assisted development practices while ensuring responsible AI use.

What you'd actually do

  1. Executes creative software solutions, design, development, and technical troubleshooting with ability to think beyond routine or conventional approaches to build solutions or break down technical problems
  2. Develops secure high-quality production code (primarily Java / Spring Boot), and reviews and debugs code written by others
  3. Leads the design and delivery of scalable microservices/APIs within the Spring ecosystem (e.g., Spring MVC/WebFlux, Spring Data, Spring Security), with strong testing practices
  4. Proactively improves engineering productivity using AI4Tech practices, including hands-on use of Copilot/Claude Code for refactoring, test generation, documentation, and code modernization—while ensuring correctness and secure coding standards
  5. Builds and operationalizes AI agents that integrate with engineering workflows (e.g., PR review assistants, runbook/support agents, remediation assistants), including tool/function calling, structured outputs, and safety/guardrails

Skills

Required

  • Java development
  • Spring Boot
  • REST APIs
  • security
  • persistence
  • unit/integration testing
  • AI4Tech hands-on experience using Copilot/Claude Code
  • building AI agents / LLM-enabled workflows
  • prompt discipline
  • grounding/verification strategies
  • safe handling of sensitive data
  • Python (scripting, automation, or AI/agent prototyping)
  • agile methodologies
  • CI/CD
  • Application Resiliency
  • Security
  • Kubernetes
  • leading effective use of approved AI-assisted software development tools
  • validating AI outputs for correctness, performance, and security
  • responsible AI use in engineering workflows
  • data sensitivity considerations
  • secure handling of inputs/outputs
  • adherence to resiliency and security expectations
  • coaching engineers on safe, compliant adoption

Nice to have

  • designing and operating production-grade agentic systems
  • observability
  • evals
  • prompt/versioning
  • fallbacks
  • rate limits
  • guardrails
  • modern microservice patterns
  • resiliency
  • distributed tracing
  • event-driven design

What the JD emphasized

  • AI agents
  • AI-assisted development tools
  • responsible AI use

Other signals

  • building AI agents
  • integrating AI into engineering workflows
  • using AI-assisted development tools