Senior Lead Software Engineer - Python, AI/LLM
About the job
- Formal training or certification on software engineering concepts and 5+ years of applied experience.
- Demonstrated experience leading effective use of enterprise-authorized AI-assisted software development tools in the work environment, including setting team expectations for validating AI outputs for correctness, performance, and security.
- Strong understanding of responsible AI use in engineering workflows, including data sensitivity, secure handling of inputs and outputs, and resiliency and security expectations; experience coaching senior engineers and leads on compliant usage patterns and controls.
- Strong hands-on system design and application development skills with demonstrated production ownership across delivery, stability, incident response, and continuous improvement.
- Advanced Python proficiency (3.10+), including idiomatic use of dataclasses, type hints, generators and streaming, CLI frameworks such as click, and sound package structure.
- Strong SQL and data-modeling skills, including correct, performant, read-only queries and reasoning about joins across large schemas and data quality.
- Hands-on experience delivering generative AI and LLM solutions, including retrieval-augmented generation, tool orchestration, evaluation, and guardrails.
- Proven experience building and maintaining authenticated API integrations using REST and streaming/WebSocket, including cookie, CSRF, Kerberos, and SSO authentication, pagination, retry/backoff, and robust error handling.
- Experience building secure, auditable systems, including versioning, access controls, credential-at-rest hygiene, data handling, logging and audit trails, monitoring, and change management.
- Data-engineering pragmatism, including 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, including pytest with fixtures, linting/type-checking, and a disciplined git/PR workflow.
- Drive adoption and governance of approved AI-assisted engineering practices across teams to improve code quality, delivery speed, and operational outcomes, including AI-assisted code review and refactoring, test acceleration, release readiness, and incident/root-cause analysis; establish measurable validation standards for secure coding, peer review, and automated testing, and promote 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, 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 using REST and streaming/WebSocket, handling cookie/CSRF/Kerberos/SSO authentication, pagination, retry/backoff, and TLS, with a focus on performance, reliability, resiliency, and security-by-design.
- Work with data scientists on data pipelines 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, focusing on maintainability, clarity, and misuse resistance.
- Build observability into services through logs, metrics, and 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, including 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 with the 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 in coding, refactoring, test creation, and troubleshooting while validating outputs for correctness, performance, and security.
- Experience with risk management domains and workflows, such as controls, operational risk, entitlements/SOX, privileged access, incident/change/problem management, and 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, including generating interactive HTML/CSS/JS dashboards such as Chart.js from Python, with basic data-visualization sense.
- Exposure to distributed computing or cloud data platforms, such as a major cloud provider, Spark, or Databricks.
About the company
JPMorgan Chase runs the largest bank in the United States, which serves households and small businesses as Chase and large companies, governments, and investors as J.P. Morgan. During the 2008 financial crisis it bought the failing investment bank Bear Stearns and lender Washington Mutual, and in 2023 it took over First Republic Bank after regulators seized it. Chase takes deposits and earns interest on credit cards, mortgages, and car loans, while the investment side earns fees for advising on mergers, raising money for companies, trading stocks and bonds, and managing wealth. Formed in a 2000 merger, JPMorgan Chase traces its roots to 1799 and is based in New York City.
Company Size
10,001+
Company Stage
IPO
Headquarters
New York City, New York
Founded
1799
Get referred to JP Morgan Chase
See people who can refer or advise you
Simplify's Take
What believers are saying
- Growth is broad-based: every JPMorgan division posted record revenue in the June 2026 quarter, and trading jumped 35%.
- Stock grants gained value: shares rose 21% in three months, valuing JPMorgan at $965 billion in August 2026.
- Tech teams are well funded: JPMorgan's nearly $20 billion yearly tech budget is the largest in banking.
What critics are saying
- AI is shrinking some teams: Dimon said in July 2026 that AI cut up to 40% of certain roles.
- Plan on five office days a week: JPMorgan ended hybrid schedules for all staff in early 2025.
- It is fighting the president in court: Trump sued JPMorgan for $5 billion in January 2026 over his closed accounts.
What makes JP Morgan Chase unique
- It ranks first in investment banking: JPMorgan earned 9.3% of global deal fees in the first half of 2026.
- It trains future CEOs: 10 Fortune 500 chiefs were JPMorgan alumni in September 2025, fifth-most of any employer.
- Its payments arm is a hidden giant: JPMorgan says it processes $12 trillion a day across 160-plus countries.
Help us improve and share your feedback! Did you find this helpful?
Benefits
Health Insurance
Flexible Work Hours
Paid Sick Leave
Paid Holidays
Growth & Insights and Company News
6 month growth
-9%1 year growth
-4%2 year growth
-4%Momei Qu, head of venture at PSP Growth, says Goldman Sachs and JPMorgan are becoming artificial intelligence (AI) stocks. She told Bloomberg's The Close that banks are tied to the AI buildout through debt financing, potential initial public offerings (IPOs) and mergers, though earnings do not show it yet. Lending was a bright spot last quarter. JPMorgan, Citigroup, and Wells Fargo posted a record $56.5 billion in combined net interest income, and JPMorgan's $107 billion outlook, excluding markets, beat the $103 billion consensus. Qu said investors are split on AI valuations: one camp excuses thin margins and heavy spending, while the other wants proof of returns. Anthropic holds its pre-IPO investor day on Wednesday. Bloomberg Intelligence analyst Herman Chan expects the Anthropic IPO to lift Goldman Sachs and Morgan Stanley. He warned that slower AI spending could cut banks' fee revenue from data center bond deals.
Four of Wall Street's biggest banks reported third quarter dealmaking fees of $8.47 billion, up 15% from a year earlier but down 7.5% from a banner second quarter. Goldman Sachs, JPMorgan Chase, Citigroup, and Wells Fargo said activity remains strong despite market volatility and higher borrowing costs. JPMorgan chief financial officer Jeremy Barnum said deals were "delayed rather than canceled" after a slowdown in late September, when volatility widened the gap between what buyers and sellers would accept. Goldman's fees rose 22% to $3.2 billion, led by record M&A advisory revenue. Wells Fargo's rose to $894 million, and Citigroup's rose 9% to $1.35 billion. Goldman chief executive officer David Solomon said some companies postponed initial public offerings (IPOs) in September rather than accept valuations 10% to 15% lower.
Goldman Sachs' equity trading revenue jumped 72% year over year to $6.44 billion in the third quarter, almost twice the $3.47 billion from fixed income. JPMorgan Chase's bond desk missed estimates by more than $500 million. JPMorgan's fixed income revenue fell 4% to $5.4 billion, its first decline in more than two years. Its equities desk rose 49% to $5.0 billion. Herman Chan, a senior US banks analyst at Bloomberg Intelligence, blamed expectations of prolonged high rates, which kept clients on the sidelines in September. "Goldman was the gold standard for the third quarter," he said. Higher rates still helped lenders. JPMorgan's net interest income rose 12.8% to $27.04 billion.
JP Morgan chief executive Jamie Dimon has warned savers against letting AI bots manage their money. He said customers could be liable for mistakes made by an agent acting on their behalf. "If people are using them, they should understand the risk," he said. JP Morgan will not let outside agents inside the company, calling it too risky for clients and the bank. The warning clashes with Silicon Valley's push. OpenAI has launched a "personal finance experience" for paid ChatGPT users in the US, and Anthropic is reportedly testing a similar tool. McKinsey found a quarter of UK consumers use AI for financial tasks at least monthly. It estimates savers could move up to £700bn out of low-interest accounts on chatbot advice.
Tenable, the exposure management company, has entered a credit agreement for a $400 million senior secured revolving credit facility. The facility is initially undrawn and gives the company more flexibility in how it allocates capital. Together with the convertible note financing announced in September, it completes the refinancing of Tenable's prior credit agreement, which included a Term Loan B facility. It also replaces the revolving credit facility that matured in July. The new loans mature on October 13, 2031, subject to a springing maturity date of 91 days inside the maturity of other material indebtedness. JPMorgan Chase Bank acted as administrative agent, and Cooley LLP advised Tenable.