Build the context backbone for governed, agentic software delivery by designing secure, scalable Code Intelligence capabilities that help engineers navigate and act on code in real time.

As a Lead Software Engineer 6 AI at JPMorganChase within the Consumer & Community Banking Code Intelligence team, you will be a hands-on technical lead building the access, relevance, and trust layers that enable AI-driven developer workflows to scale safely. You will design and deliver distributed systems that combine retrieval, ranking, and security controls to accelerate engineering outcomes across a large, complex codebase.

Job responsibilities

• Design and deliver an entitlements model that ensures code context and AI responses respect repository-level read permissions and access boundaries, enabling safe scale-up beyond pilot.
• Build context prioritization and relevance ranking scoped to user context (for example, team ownership and service affinity) to improve response quality and reduce cost per query at scale.
• Implement trust and quality signals for AI output, including grounding, citation accuracy, and freshness metrics, establishing measurable standards for governed autonomy.
• Architect and develop production-grade services on AWS (for example, containers, serverless, queues, search, and relational data stores), applying best practices for scalability, observability, and cost efficiency.
• Own deep cross-system debugging and integration across event-driven ingestion, indexing, retrieval, and serving pathways.
• Drive technical design reviews and mentor engineers through hands-on leadership, clear standards, and strong engineering judgment.
• Drives team adoption of enterprise-authorized AI-assisted engineering practices within the work environment to improve code quality, delivery speed, and operational outcomes, 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.

Required qualifications, capabilities, and skills

• Formal training or certification on software engineering concepts and 5+ years applied experience.
• Hands-on experience designing and delivering distributed systems in a production AWS environment.
• Proficiency with retrieval-augmented generation architectures, including chunking strategies, embeddings, and vector + lexical search (for example, OpenSearch, pgvector, FAISS).
• Experience building and operating agentic tooling, such as tool-use patterns with large language models, agent orchestration frameworks, or MCP-based integrations.
• Proficiency in Java or Python and experience with event-driven architectures (for example, SQS, SNS, Kafka).
• Strong understanding of access control design, entitlements models, and data boundary enforcement within a regulated enterprise environment.
• Experience with continuous integration and delivery, containerization (for example, Docker, ECS/EKS), and infrastructure-as-code.
• 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.

Preferred qualifications, capabilities, and skills

• Experience with model invocation services (for example, AWS Bedrock) and working with modern large language models in production.
• Experience building or operating code intelligence platforms, such as code search, static analysis, repository metadata systems, or large-scale indexing pipelines.
• Familiarity with evaluation approaches for AI systems (offline/online quality measurement) and guardrail patterns for production deployments.
• Experience with Spring Boot or similar enterprise service frameworks.
• Experience creating reusable agent skills or patterns that accelerate delivery across engineering teams.