Help shape how teams across the firm build AI agents. You will lead engineering for a flagship, high-visibility AI Agent Platform—the SDK, orchestration frameworks, and reusable components that power agentic AI experiences across the organization. Beyond any single chat experience, you will own the foundational tooling that lets teams compose agents—conversational, voice, and document-extraction—ground them in enterprise data, give them durable agentic memory, and continuously improve accuracy on hard capabilities like NL2SQL and RAG. You will raise delivery standards, turn complex problems into reliable production systems, and set the quality bar for infrastructure that many teams and thousands of users depend on. Join a team where strong engineering, thoughtful collaboration, and continuous learning are core to how we operate.
As Lead Software Engineer – AI Agent Platform at JPMorganChase within Enterprise Technology, AI and Machine Learning & Data Platforms, you will lead the technical design and delivery of the SDK and platform capabilities that enable large-language-model-powered agents at scale. You will own the building blocks agent orchestration, tool/function calling, retrieval and grounding, voice interaction, document extraction, and agentic memory and drive measurable, iterative improvement ("hill-climbing") of capabilities such as NL2SQL and RAG. You will translate high-impact problems into production-grade solutions, from discovery and design through deployment and ongoing operations, while partnering closely with product and stakeholder groups to deliver measurable outcomes.
Job responsibilities- Lead end-to-end delivery of the AI Agent Platform SDK and frameworks—from problem framing and technical design through production deployment, scaling, and monitoring—that engineering teams use to build, evaluate, and operate AI agents.
- Own core platform services and reusable building blocks: agent orchestration, tool/function calling, retrieval-augmented generation pipelines, and model-serving integration.
- Build and operate first-class agent modalities on the platform, including voice agents (speech-to-text, text-to-speech, low-latency streaming, and turn-taking), document-extraction agents (parsing, OCR, structured field and table extraction from complex documents), and agentic memory (short- and long-term memory, persistence, retrieval, and context management across sessions).
- Drive systematic hill-climbing of core agent capabilities—including NL2SQL, RAG, voice, document extraction, and tool use—by building evaluation datasets, benchmarks, and quality metrics, then iterating on prompts, retrieval, and orchestration to measurably improve accuracy.
- Establish engineering standards through hands-on system design, rigorous code review, and mentorship to improve reliability, maintainability, latency, and developer experience for teams building on the SDK.
- Build and operationalize evaluation, testing, and observability capabilities (offline eval harnesses, regression suites, tracing, latency and cost telemetry, logs, and analytics) to continuously improve solution quality.
- Implement robust safety and governance patterns—guardrails, content filtering, prompt-injection defenses, access controls, and audit-ready operational practices aligned to enterprise expectations.
- Partner with product managers and stakeholders to shape the roadmap, define success metrics (capability accuracy, adoption, task completion, quality), and prioritize work that delivers measurable business impact.
- Drive cross-functional alignment across engineering, data, security, and risk partners to ensure the platform is secure, stable, performant, and scalable.
- Contribute to technical documentation, SDK references, reference implementations, and enablement content that accelerates adoption and responsible usage.
- Formal training or certification on applied artificial intelligence and machine learning concepts and 5+ years applied experience.
- Advanced proficiency in Python with strong software engineering fundamentals, including testing, design patterns, version control, and code review practices.
- Hands-on experience building, evaluating, and deploying machine learning or large-language-model-enabled systems into production environments—ideally reusable libraries, SDKs, or platform services consumed by other engineering teams.
- Practical experience with prompt engineering and retrieval-augmented generation, including building evaluation methods, benchmarks, and quality measurement to systematically improve capabilities such as NL2SQL and RAG.
- Experience designing and operating reliable services, including incident response readiness, performance tuning, and operational stability for data-intensive systems.
- Demonstrated ability to lead technical decisions and deliver outcomes through ambiguity, balancing speed, risk, and long-term maintainability.
- Strong communication skills with the ability to explain technical trade-offs to both technical and non-technical stakeholders.
- Experience with agent orchestration frameworks (for example, LangGraph, LlamaIndex, Google ADK, or custom orchestration) and evaluation tooling for LLM systems.
- Experience building voice agents (speech recognition, text-to-speech, real-time streaming audio, and conversational turn-taking).
- Experience building document-extraction / intelligent document-processing agents (OCR, layout parsing, structured field and table extraction from complex or unstructured documents).
- Experience implementing agentic memory systems—short- and long-term memory, persistence, and context retrieval across sessions.
- Familiarity with vector databases, embedding pipelines, or graph-based memory approaches used in retrieval-augmented generation solutions.
- Experience with continuous integration and continuous delivery practices and containerization (Docker and Kubernetes) for production deployments.
- Experience with cloud and machine learning platforms (for example, Amazon Web Services, Databricks, or comparable platforms).
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.
#LI-RB3
#AMDPAIML
About Us
We offer a competitive total rewards package including base salary determined based on the role, experience, skill set and location. Those in eligible roles may receive commission-based pay and/or discretionary incentive compensation, paid in the form of cash and/or forfeitable equity, awarded in recognition of individual achievements and contributions. We also offer a range of benefits and programs to meet employee needs, based on eligibility. These benefits include comprehensive health care coverage, on-site health and wellness centers, a retirement savings plan, backup childcare, tuition reimbursement, mental health support, financial coaching and more. Additional details about total compensation and benefits will be provided during the hiring process.
We recognize that our people are our strength and the diverse talents they bring to our global workforce are directly linked to our success. We are an equal opportunity employer and place a high value on diversity and inclusion at our company. We do not discriminate on the basis of any protected attribute, including race, religion, color, national origin, gender, sexual orientation, gender identity, gender expression, age, marital or veteran status, pregnancy or disability, or any other basis protected under applicable law. We also make reasonable accommodations for applicants’ and employees’ religious practices and beliefs, as well as mental health or physical disability needs. Visit our FAQs for more information about requesting an accommodation.
JPMorgan Chase & Co. is an Equal Opportunity Employer, including Disability/Veterans
Skills Required
- Formal training or certification in applied artificial intelligence and machine learning concepts
- 5+ years of applied artificial intelligence and machine learning experience
- Advanced proficiency in Python
- Strong software engineering fundamentals, including testing, design patterns, version control, and code reviews
- Experience building, evaluating, and deploying machine learning or large-language-model systems in production
- Experience building reusable libraries, SDKs, or platform services consumed by engineering teams
- Practical experience with prompt engineering and retrieval-augmented generation
- Experience building evaluation methods, benchmarks, and quality measurements for NL2SQL and RAG
- Experience designing and operating reliable data-intensive services
- Experience with incident response readiness, performance tuning, and operational stability
- Ability to lead technical decisions and deliver outcomes amid ambiguity
- Strong communication skills with technical and non-technical stakeholders
- Experience with agent orchestration frameworks such as LangGraph, LlamaIndex, Google ADK, or custom orchestration
- Experience building voice agents, including speech recognition, text-to-speech, streaming audio, and conversational turn-taking
- Experience building document-extraction or intelligent document-processing agents
- Experience implementing agentic memory systems
- Familiarity with vector databases, embedding pipelines, or graph-based memory approaches
- Experience with continuous integration, continuous delivery, Docker, and Kubernetes
- Experience with cloud and machine learning platforms such as Amazon Web Services or Databricks
JPMorganChase Compensation & Benefits Highlights
The following summarizes recurring compensation and benefits themes identified from responses generated by popular LLMs to common candidate questions about JPMorganChase and has not been reviewed or approved by JPMorganChase.
-
Healthcare Strength — Medical coverage and wellness resources, including mental-health support and wellness incentives, are described as comprehensive and accessible; feedback suggests income-based contributions help keep care affordable.
-
Retirement Support — A dollar-for-dollar 401(k) match up to 5% of eligible pay, plus additional employer contributions in some cases, is highlighted as a strong pillar of financial security. Feedback suggests this structure is a notable advantage of the total rewards package.
-
Parental & Family Support — Up to 16 weeks of paid parental leave for all parents, along with fertility, adoption, surrogacy, childcare, and family-support resources, signals a family-forward approach. Feedback suggests these programs are a standout feature of the package.
JPMorganChase Insights
What We Do
JPMorgan Chase & Co. (NYSE: JPM) is a leading global financial services firm with assets of $3.7 trillion and operations worldwide. The firm is a leader in investment banking, financial services for consumers and small businesses, commercial banking, financial transaction processing, and asset management. A component of the Dow Jones Industrial Average, JPMorgan Chase & Co. serves millions of consumers in the United States and many of the world’s most prominent corporate, institutional and government clients under its J.P. Morgan and Chase brands. Technology fuels every aspect of our company and is at the heart of everything we do. With over 50,000 technologists globally and an annual tech spend of $12 billion, we are dedicated to improving the design, analytics, development, coding, testing and application programming that goes into creating high quality software and new products. Learn more about technology at our firm, explore resources from our Distinguished Engineers, AI & ML researchers, and other experts; access the latest episode of our TechTrends podcast, and more at www.jpmorgan.com/technology. Information about JPMorgan Chase & Co. is available at www.jpmorganchase.com. ©2023 JPMorgan Chase & Co. All rights reserved. JPMorgan Chase is an Equal Opportunity Employer, including Disability/Veterans.
Why Work With Us
Our technologists work on a diverse range of solutions that include strategic technology initiatives, big data, mobile, electronic payments, machine learning, cybersecurity, enterprise cloud development, and other state-of-the-art technologies.
Gallery





.png)