Senior Lead Software Engineer - Python - AI/LLM

Be an integral part of an agile team that's constantly pushing the envelope to enhance, build, and deliver top-notch technology products. As a Senior Lead Software Engineer at JPMorganChase within the Chief Technology Office - Risk, Control & Regulatory team, you are an integral part of an agile team that works to enhance, build, and deliver trusted market-leading technology products in a secure, stable, and scalable way. Drive significant business impact through your capabilities and contributions, and apply deep technical expertise and problem-solving methodologies to tackle a diverse array of challenges that span multiple technologies and applications. You will develop Python-based software that combines data pipelines, authenticated internal-system integrations, and generative AI/LLM-based agent capabilities. You will focus on a Python and PostgreSQL platform, backed by a curated risk data store and an architecture of LLM agents and skills. You will contribute production code regularly, raise the engineering quality bar through strong technical judgment and collaboration, and ensure solutions are reliable, well-observed, and compliant with firm expectations for security, data sensitivity, and responsible AI use. Job responsibilities Drives adoption and governance of approved AI-assisted engineering practices across teams to improve code quality, delivery speed, and operational outcomes (e.g., AI-assisted code review/refactoring, test acceleration, release readiness, incident/root-cause analysis), while establishing measurable validation standards (secure coding, peer review, automated testing) and promoting reuse of proven patterns and automation within the SDLC/TLM toolchain. Build and maintain the full-stack Python toolkit and data products that power agentic risk-oversight workflows Implement LLM-based services, including retrieval-augmented generation (RAG), tool/function calling, agent and skill orchestration, prompt/version management, and evaluation/guardrails aligned to risk and control expectations. Develop authenticated integrations and APIs to internal systems (REST and streaming/WebSocket), handling cookie/CSRF/Kerberos/SSO auth, pagination, retry/backoff, and TLS, with a focus on performance, reliability, resiliency, and security-by-design. Work on data pipelines with our Data Scientist’s that stream and normalize large datasets and join them across sources against large schemas, using correct, performant, read-only SQL. Write secure, high-quality production code and comprehensive tests; contribute actively to code reviews (as author and reviewer) with a focus on maintainability, clarity, and misuse resistance. Build observability into services (logs/metrics/tracing), troubleshoot production issues, participate in incident response as needed, and automate remediation for recurring operational problems. Implement safe-by-default patterns for AI features (e.g., bounded tool use, validation, timeouts, structured outputs, audit trails, and human-in-the-loop workflows where appropriate). Generate audience-ready outputs, including self-contained interactive HTML dashboards and structured evidence packages, calibrated for technical and non-technical risk stakeholders. Collaborate in our product team to refine requirements, break down work, and deliver iteratively in partnership with Product, Risk, Controls, Compliance, and data teams. Use enterprise-authorized AI-assisted engineering tools responsibly to accelerate delivery (coding, refactoring, test creation, troubleshooting) while validating outputs for correctness, performance, and security. Required qualifications, capabilities, and skills Formal training or certification on software engineering concepts and 5+ years applied experience Demonstrated experience leading effective use of enterprise-authorized AI-assisted software development tools within the work environment (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 senior engineers/leads on compliant usage patterns and controls. Strong hands-on system design and application development skills with demonstrated production ownership (delivery, stability, incident response, and continuous improvement). Advanced Python proficiency (3.10+), including idiomatic use of dataclasses, type hints, generators/streaming, CLI frameworks (e.g., click), and sound package structure. Strong SQL and data-modeling skills: correct, performant, read-only queries and confident reasoning about joins across large schemas and data quality. Hands-on experience delivering generative AI/LLM solutions, including RAG, tool orchestration, evaluation, and guardrails. Proven experience building and maintaining authenticated API integrations (REST and streaming/WebSocket), including cookie/CSRF/Kerberos/SSO auth, pagination, retry/backoff, and robust error handling. Experience building secure, auditable systems (versioning, access controls, credential-at-rest hygiene, data handling, logging/audit trails, monitoring, and change management). Data-engineering pragmatism: streaming large files, header/key normalization, fuzzy joins, and memory-conscious ETL over dirty, real-world data. Experience building and testing production Python with modern CI/CD practices (e.g., pytest with fixtures, linting/type-checking, and a disciplined git/PR workflow). Preferred qualifications, capabilities, and skills Experience with risk management domains and workflows (e.g., controls, operational risk, entitlements/SOX, privileged access, incident/change/problem management, model risk) and building in regulated environments Experience authoring LLM agent/skill systems, knowledge-base/RAG design, and MCP-based tooling. Frontend-lite reporting skills: generating interactive HTML/CSS/JS dashboards (e.g., Chart.js) from Python, with basic data-visualization sense. Exposure to distributed computing or cloud data platforms (e.g., a major cloud provider, Spark, or Databricks).