Lead Software Engineer - AI Application

JPMorgan Chase & Co.; Jersey City (NJ); On-site; USD 180,000 - 250,000; Full time

Job summary

JPMorganChase within Corporate Technology is seeking a Lead Software Engineer to steer the architecture and hands-on delivery of scalable GenAI applications and agentic AI platforms for finance use cases. You will design cloud-native AWS services, implement evaluation and observability standards, and drive cross-team technical decisions to improve reliability, cost, and velocity.

The role demands advanced Python proficiency, proven delivery of LLM/agentic systems, and strong technical leadership

Qualifications

• 5+ years of applied software engineering experience.
• Experience shipping production large language model apps with agentic workflows.
• Proven ability to guide AI-assisted software development and code reviews.
• Strong focus on secure, resilient and compliant AI in enterprise.
• Familiarity with agentic workflows and frameworks (LangChain, LangGraph, Autogen, CrewAI, A2A).
• Experience with embeddings, vector databases and prompt lifecycle/versioning.

Responsibilities

• Lead architecture and hands-on delivery of scalable agentic AI platforms for enterprise workflows.
• Drive adoption of enterprise-authorized AI engineering practices to improve code quality and delivery speed.
• Apply SDLC tools and automation to increase value from AI capabilities.
• Design and build production-grade AI systems including agents, skills, memory patterns, and tool-use orchestration.
• Architect retrieval and context-engineering approaches (embeddings, semantic search, grounding).
• Engineer cloud-native AI services on AWS using containers and serverless patterns.
• Optimize platform performance across latency, throughput, scalability, caching, and cost controls.
• Build well-governed APIs and integrations connecting AI to enterprise platforms and processes.
• Establish evaluation, experimentation, regression testing, and observability frameworks.
• Mentor senior engineers and drive cross-team architecture decisions.

Skills

Advanced Python

LLM/agentic systems

Technical leadership

Cloud-native AWS

Observability & testing

Mentor engineers

Education

Software engineering certification

Tools

AWS Bedrock

Kubernetes

LangChain

LangGraph

Autogen

Job description

We have an opportunity to impact your career and provide an adventure where you can push the limits of what's possible. As a Lead Software Engineer at JPMorganChase within Corporate Technology, you will lead the architecture and hands-on implementation of scalable GenAI Applications and agentic AI platforms for Finance use cases leveraging Firmwide AI tools & platforms. You will design cloud-native solutions, establish evaluation and observability standards, and drive technical decisions across teams to improve reliability, cost, and developer velocity. The candidate will design cloud-native AWS services and reusable platform capabilities (agents, retrieval/RAG, guardrails, tool orchestration, APIs), while establishing strong evaluation, observability, reliability, security, and cost controls. Ideal candidates have extensive experience, advanced Python, proven delivery of LLM/agentic systems, and technical leadership skills to mentor engineers and drive cross-team architecture standards in a regulated enterprise environment.

Job responsibilities

• Lead the architecture and hands-on delivery of scalable, reliable agentic AI platforms for enterprise workflows
• 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.
• Design and build production-grade AI systems including agents, skills, memory patterns, guardrails, and tool-use orchestration
• Architect retrieval and context-engineering approaches including embeddings, semantic search, grounding, summarization, and prompt/version management
• Engineer cloud-native AI services on AWS using containers and serverless patterns, event-driven messaging, and distributed data stores
• Optimize platform performance across latency, throughput, scalability, caching, context efficiency, and cost controls
• Build well-governed APIs and integrations that connect AI capabilities to enterprise platforms, tools, and business processes
• Establish evaluation, experimentation, regression testing, and observability frameworks to continuously improve quality and agent behavior
• Mentor senior engineers and influence engineering direction through code reviews, architecture forums, and cross-team technical leadership
• 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.

Required qualifications, capabilities and skills

• Formal training or certification on software engineering concepts and 5+ years applied experience
• Experience architecting and shipping production large language model applications, including agentic workflows and tool integration patterns
• Demonstrated experience leading effective use of approved AI-assisted software development tools (e.g., for coding, code review, test acceleration, troubleshooting) with the ability to set team expectations for validating AI outputs for correctness, performance, and security.
• Strong understanding of responsible AI use in engineering workflows, including data sensitivity considerations, secure handling of inputs/outputs, and adherence to resiliency and security expectations; experience coaching engineers on safe, compliant adoption within delivery practices
• Familiarity with agentic workflows and frameworks (e.g., LangChain, LangGraph, Autogen, CrewAI and A2A etc)
• Experience building retrieval-augmented generation solutions (embeddings, semantic search, grounding) using Vector databases and managing prompt lifecycle/versioning
• Strong software engineering fundamentals with ability to deliver cloud-native services using containers and serverless designs on AWS
• Advanced python programming skills with experience writing production quality code
• Build systems using frontier models from OpenAI, Anthropic or others leveraging platforms such as AWS Bedrock / Google Vertex AI or other similar platforms
• Proven technical leadership skills, including mentoring, driving architecture decisions, and influencing cross-functional stakeholders
• 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.

Preferred qualifications, capabilities and skills

• Experience building standardized evaluation harnesses, automated regression suites, and experimentation platforms for large language model systems
• Hands-on experience with Kubernetes-based deployment patterns and operational excellence practices for high-availability services
• Experience applying privacy, data minimization, and safe AI guardrail patterns in regulated or high-risk environments
• Familiarity with context-efficiency optimization techniques and cost governance for large language model workloads
• Experience building reusable developer platforms, reference architectures, and technical standards across multiple teams