Lead Software Engineer - Java/Python/AWS/AI/LLM

JPMorganChase•Plano, TX

About The Position

As a Lead Software Engineer at JPMorganChase within Consumer & Community Banking, OPS Tech, you will contribute to an agile team building and enhancing secure, stable, scalable technology products. You will deliver critical technology solutions across multiple technical areas in support of the firm’s business objectives, primarily using Java and, as needed, Python, along with AWS and related technologies. The role combines full-stack software development, cloud-native architecture, AI and LLM integration, engineering leadership, and production reliability. You will guide engineers and team practices, establish engineering standards, and help deliver predictable, secure software releases. You will also collaborate across initiatives, communicate risks and status, and participate in Scrum and Agile ceremonies.

Requirements

Formal training or certification in Software Engineering and at least 5 years of applied experience building production systems.
Strong system design, application development, and production operational stability skills, including on-call and incident ownership.
Expertise designing and building microservices and RESTful APIs, with strong knowledge of data technologies and integration patterns.
Hands-on experience building cloud-native systems on at least one major cloud platform: AWS, GCP, or Azure.
Experience with distributed systems concepts, including scalability, resiliency, concurrency, idempotency, failure modes, and performance tuning.
Ability to influence product design and technical direction by proposing pragmatic architectures, tradeoffs, and standards aligned with firm SDLC, security, and controls expectations.
Hands-on experience using enterprise-authorized AI-assisted software development tools at work, and evaluating, validating, and refining AI-generated outputs for correctness, performance, and security.
Experience leading effective team use of approved AI-assisted development practices, including coding, code review, test acceleration, and troubleshooting, and establishing expectations and reusable validation patterns.
Hands-on experience with LLMs and generative AI use cases, such as RAG, summarization or extraction, and workflow assistants, including evaluation and monitoring considerations.
Understanding of responsible AI use in engineering workflows, including data sensitivity, safe handling of inputs and outputs, and resiliency and security expectations; ability to guide peers on safe and effective usage.
Strong communication and stakeholder management skills, including the ability to deliver across multiple initiatives and drive outcomes through ambiguity.

Nice To Haves

AWS cloud certification(s).
AI/ML or GenAI certification(s), or equivalent practical experience delivering LLM-enabled capabilities.
Advanced Java proficiency and working knowledge of Python.
Experience with Docker, Kubernetes, and modern CI/CD practices.
Experience with multi-region deployments, disaster recovery, and zero-downtime release patterns.
Strong understanding of responsible AI practices, including prompt and agent safety patterns and secure handling of sensitive data.
Track record delivering scalable, reliable, and secure products from concept to launch in a regulated environment.
Familiarity with financial services technology; IVR/CCaaS experience is a plus.

Responsibilities

Design and develop full-stack software solutions aligned with business outcomes.
Build AI-driven capabilities, including LLM-based services, orchestration, and integrations into business workflows.
Architect and deliver secure, scalable, resilient, high-performance cloud-native microservices and APIs.
Lead adoption of enterprise-authorized AI-assisted engineering tools and practices, establishing validation standards and promoting reusable patterns.
Mentor and develop engineers through code reviews, pairing, technical guidance, and feedback.
Establish team engineering standards for architecture, coding, testing, and operational readiness.
Define and operate service reliability practices, including SLIs/SLOs, incident response, root-cause analysis, postmortems, and reliability improvements.
Identify recurring operational issues and automate remediation to improve system stability and observability, including logs, metrics, and tracing.
Build and maintain CI/CD pipelines and release strategies, including quality gates, canary or blue-green releases, rollback, and feature flags.
Communicate status and risks, manage priorities and dependencies across initiatives, collaborate in a Scrum team, and participate in Agile ceremonies.
Deliver production code primarily in Java and, as needed, Python, using AWS and related technologies.