AI Engineer - Lead Software Engineer

The role focuses on architecting scalable AI platforms and agentic systems for enterprise workflows within JPMorganChase's Enterprise Technology organization, with emphasis on cloud-native design on AWS, observability, and cross-team reliability improvements.

Location: Jersey City, NJ (onsite). Salary: USD 152,000 - 215,000 per year. Minimum experience: 5 years.

Responsibilities

• Direct the design and practical delivery of scalable, dependable agentic AI platforms that support enterprise processes.
• Architect and implement production-ready AI components such as agents, skills, memory patterns, guardrails, and orchestration of tool usage.
• Develop retrieval and context-engineering strategies involving embeddings, semantic search, grounding, summarization, and prompt/version lifecycle management.
• Develop cloud-native AI services on AWS leveraging containers, serverless patterns, event-driven messaging, and distributed data stores.
• Enhance platform performance focusing on latency, throughput, scalability, caching efficiency, context reuse, and cost containment.
• Create well-governed APIs and integrations linking AI capabilities to enterprise platforms, tools, and business processes.
• Establish evaluation, experimentation, regression testing, and observability frameworks to continuously improve model quality and agent behavior.
• Define engineering standards for reliability, security, and safe AI operation across the platform lifecycle.
• Mentor senior engineers and shape engineering direction via code reviews, architecture discussions, and cross-team leadership.
• Utilize enterprise-approved AI-assisted development tools to improve code quality, speed, and productivity on complex deliverables, with outputs validated through peer review, automated testing, and secure coding practices.
• Share learnings and reusable patterns to raise overall team effectiveness.
• Apply SDLC toolchain knowledge, including enterprise-approved AI-assisted development and automation capabilities, to maximize automation value.

Requirements

• Formal software engineering training or certification complemented by at least five years of hands-on experience.
• Experience designing and delivering production-grade large language model applications, including agentic workflows and tool integration patterns.
• Solid software engineering fundamentals with the ability to deliver cloud-native services on AWS using containers and serverless designs.
• Proficiency in designing distributed systems with asynchronous workflows, durable messaging, and scalable data access patterns.
• Experience building retrieval-augmented generation solutions, including embeddings, semantic search, grounding, and managing prompt lifecycles and versioning.
• Proven ability to implement evaluation and monitoring approaches for model quality, reliability, and safe behavior over time.
• Strong API design skills with secure integration patterns and reusable platform capabilities.
• Proven technical leadership, including mentoring, guiding architectural decisions, and influencing stakeholders across teams.
• Hands-on experience with enterprise-approved AI-assisted development tools for coding, testing, debugging, or documentation, plus ability to critically evaluate and validate AI-generated outputs for correctness, performance, and security.
• Understanding of responsible AI use in engineering workflows, including data sensitivity, secure input/output handling, and adherence to resiliency and security standards; ability to guide peers on safe AI usage within teams.

Technologies

• AWS
• Kubernetes
• LLM Suite

Benefits

• comprehensive health care coverage
• on-site health and wellness centers
• retirement savings plan
• backup childcare
• tuition reimbursement
• mental health support
• financial coaching

FEDERAL DEPOSIT INSURANCE ACT

• This position is subject to Section 19 of the Federal Deposit Insurance Act. As such, an employment offer for this position is contingent on JPMorganChase's review of criminal conviction history, including pretrial diversions or program entries.