We are building the next generation of intelligent, cloud-native systems — and we want you to help lead the way. At JPMorganChase, you'll work at the intersection of software engineering, artificial intelligence, and cloud infrastructure, delivering solutions that matter at scale. This is an opportunity to grow your craft, shape engineering standards, and make a measurable impact on how the firm builds and operates technology.
As a Lead Software Engineer at JPMorganChase, you will own the delivery of complex, AI-powered software initiatives from discovery through production with minimal supervision. You will design and build intelligent systems leveraging large language models and agentic approaches, expose capabilities through well-designed APIs and microservices, and operate confidently across a multi-cloud environment — ensuring portability, security, and reliability at every layer.
Job responsibilities
- Lead initiatives end-to-end — from requirements clarification and architecture through implementation, testing, release, and production support — with strong ownership and minimal supervision
- Design and implement AI solutions using large language models and modern agent patterns, including prompting strategies, tool/function calling, retrieval patterns, routing, and memory/state management where applicable
- Build guardrails, evaluation frameworks, monitoring pipelines, and cost/latency optimizations for production LLM-based systems
- Design, build, and operate REST and gRPC APIs and microservices, defining clear contracts using OpenAPI and Protobuf while ensuring backward compatibility, authentication, rate limiting, and observability
- Apply resilience engineering patterns — including timeouts, retries, and circuit breakers — to ensure reliable, production-grade service behavior
- Build and maintain well-tested, maintainable Python services and automation with clear packaging, dependency management, and architectural standards
- Own data design and implementation, including schema design, data access patterns, and complex SQL optimization aligned to performance and reliability requirements
- Build and manage infrastructure as code using Terraform, supporting containerized deployments via Kubernetes and CI/CD pipelines across multi-cloud environments
- Drive engineering excellence across code quality, testing strategy, performance, reliability, and operational rigor, including leading root-cause analysis for complex production issues
- Mentor engineers, provide technical guidance, and establish standards for delivery and engineering practices across the team
- 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 automations.
Required qualifications, capabilities, and skills
- Formal training or certification on software engineering concepts and advanced applied experience
- Proven track record leading software delivery end-to-end with strong ownership and the ability to execute independently across the full development lifecycle
- Strong Python software engineering skills for building production-grade services and automation, with solid testing, packaging, and maintainability practices
- Strong understanding of relational databases and SQL, including schema design, query optimization, indexing, and transaction management
- Demonstrated experience building AI solutions using large language models in production environments, including quality assurance, safety controls, evaluation, observability, and cost management
- Strong API and microservices engineering experience, including service design, contract definition, security patterns, performance tuning, and distributed system observability
- Hands-on multi-cloud experience (AWS preferred) with strong distributed systems fundamentals and a portability-minded approach to design
- Strong Terraform skills for infrastructure-as-code, module design, environment management, and remote state handling
- Working knowledge of DevOps practices including CI/CD pipelines, Git-based workflows, and Kubernetes deployments
- 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 practicests.
Preferred qualifications, capabilities, and skills
- Experience designing and building agentic architectures, including tool use, planning and execution loops, and multi-step workflow orchestration
- Experience building reusable internal libraries or frameworks that accelerate team delivery and promote engineering consistency
- Familiarity with advanced LLM evaluation techniques, including automated benchmarking, red-teaming, and latency/cost profiling in production
- Experience with gRPC and Protobuf-based service design in distributed, high-throughput environments
- Exposure to platform or developer experience engineering, including internal tooling, shared infrastructure patterns, or delivery enablement frameworks.