Lead development of production AI agents and machine learning workflows for B2B agentic commerce and payments. Responsibilities include agent orchestration, negotiation, onboarding, model training and serving on Kubernetes, evaluation, observability, secure software development, model-risk documentation, and technical leadership. The role also guides AI-assisted engineering practices and evaluates architectures with vendors and internal teams.
Join us to shape the future of payments technology and agentic commerce. You will have the opportunity to build impactful solutions, collaborate with talented teams, and advance your career in a dynamic environment. We value creativity, inclusivity, and continuous learning, empowering you to push boundaries and deliver market-leading products. Experience the excitement of working with cutting-edge AI and ML tools while making a difference in the financial industry.
As a Lead Software Engineer in Payments Technology within the Commercial and Investment Bank, you will play a pivotal role in designing, developing, and delivering trusted technology products. You will own major components of our B2B agentic commerce agents end to end, from multi-agent negotiation and onboarding to production ML model workflows. You will help drive secure, stable, and scalable solutions, foster a collaborative team culture, and contribute to the advancement of AI-powered payments. Your expertise will directly impact our technology and the clients we serve.
Job Responsibilities:
- Execute creative software solutions, design, development, and technical troubleshooting
- Own the design and delivery of production agents, including orchestration, negotiation, supplier onboarding, and outreach
- Build production paths for optimization and prediction models, including training, automated testing, and serving on Kubernetes
- Design agent workflows that ensure pricing, eligibility, and policy decisions remain in deterministic services
- Develop secure, high-quality production code and review and debug code written by others
- Establish evaluation and observability for agents and models, including regression suites, scoring, traces, and performance monitoring
- Prepare agents and models for model risk review, producing documentation, test evidence, and controls
- Drive team adoption of enterprise-authorized AI-assisted engineering practices to improve code quality and delivery speed
- Apply knowledge of tools within the Software Development Life Cycle toolchain to enhance automation
- Identify opportunities to eliminate or automate remediation of recurring issues
- Lead evaluation sessions with external vendors, startups, and internal teams to assess architectural designs and technical credentials
Required Qualifications, Capabilities, and Skills:
- Formal training or certification in software engineering concepts
- Hands-on experience delivering system design, application development, testing, and operational stability
- Advanced proficiency in Python and proficiency in one or more additional languages (e.g., Java, TypeScript)
- Experience shipping LLM-based applications or agents to production, including tool calling, retrieval, and evaluation
- Experience productionizing ML models, including training pipelines, model registries, CI/CD for models, and serving behind APIs
- Demonstrated experience leading effective use of approved AI-assisted software development tools
- Strong understanding of responsible AI use in engineering workflows, including data sensitivity and secure handling
- Proficiency in all aspects of the Software Development Life Cycle
- Advanced understanding of agile methodologies such as CI/CD, Application Resiliency, and Security
- In-depth knowledge of the financial services industry and IT systems
- Practical cloud native experience
- Proficiency with Kubernetes and Amazon EKS, micro-VM isolation, and sidecar patterns, with hands-on experience applying security at multiple layers
Preferred Qualifications, Capabilities, and Skills:
- Experience with agent frameworks and protocols (Google ADK, LangGraph, MCP, A2A, AG-UI)
- Experience with Databricks, MLflow, Spark, and Delta Lake or Apache Iceberg
- Experience serving models on Kubernetes, including GPU workloads and fine-tuned small language models
- Experience with optimization or pricing models and exposing them as services
- Experience with fine-grained authorization and OpenTelemetry
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.
JPMorganChase London, England Office
25 Bank Street, Canary Wharf, London, United Kingdom, E14 5JP
Similar Jobs
Financial Services
Lead architecture and engineering for B2B agentic commerce and machine-learning systems in global payments. Define multi-agent architectures, authorization, information barriers, MLOps pipelines, evaluation frameworks, safety guardrails, and model-risk evidence. Develop and review secure production code, establish AI-assisted engineering standards, integrate external agents, improve operational resilience, and guide technical teams and vendors. The role requires advanced Python, production LLM agent experience, secure distributed-systems expertise, and financial-services technology knowledge.
Top Skills:
A2AAg-UiCi/CdDatabricksDistributed SystemsGoogle AdkGpu InferenceGraphragIdentity And AuthorizationKnowledge GraphsKubernetesLanggraphLlm AgentsMcpMicro-Vm IsolationMl PlatformsMlflowMlopsMulti-Agent SystemsOpa/RegoOpenfgaPythonService Mesh
.png)
Fintech • Information Technology • Payments • Productivity • Software • Travel • Automation
Own the vision, strategy, roadmap, and execution of Navan’s payments platform, including expense payments, payouts, routing, settlement, reconciliation, banking integrations, and international expansion. Partner cross-functionally to launch scalable, compliant payment capabilities, manage technical complexity and risk, and optimize performance using data and analytics.
Top Skills:
AIBanking IntegrationsPayment Processing SystemsPayment RailsPayment Service Providers
Artificial Intelligence • Cloud • HR Tech • Information Technology • Productivity • Software • Automation
Build and deploy production-grade, LLM-enabled applications for strategic customers. Own backend services, data orchestration, frontend integrations, APIs, vector databases, LLM pipelines, and reusable AI tooling. Work directly with customers in agile field deployments, integrate legacy systems, improve developer experience, and influence platform strategy. Deliver secure, scalable solutions while creating libraries, SDKs, prompts, scaffolds, and documentation that accelerate future enterprise AI implementations.
Top Skills:
AngularAWSAzureCi/CdContainersDistributed SystemsGCPGraphQLInfrastructure As CodeJavaLangchainLlmsMonitoringNode.jsPrompt ChainingPythonReactRestSemantic KernelVector DatabasesVector Search
What you need to know about the London Tech Scene
London isn't just a hub for established businesses; it's also a nursery for innovation. Boasting one of the most recognized fintech ecosystems in Europe, attracting billions in investments each year, London's success has made it a go-to destination for startups looking to make their mark. Top U.K. companies like Hoptin, Moneybox and Marshmallow have already made the city their base — yet fintech is just the beginning. From healthtech to renewable energy to cybersecurity and beyond, the city's startups are breaking new ground across a range of industries.
