AI/ML Senior Lead Software Engineer - Agentic Pricing

JPMorganChase•Jersey City, NJ

About The Position

As a Senior Lead Software Engineer at JPMorganChase within Commercial and Investment Bank Digital & Platform Services, Data Analytics, you will help an agile team build, enhance, and deliver secure, stable, scalable, market-leading technology products. You will use deep technical expertise and problem-solving skills to tackle challenges across technologies and applications, providing significant business impact. The role focuses on designing and shipping production AI agents on NEO across a federated portfolio, from prototype through production. You will build reliable retrieval systems, including Graph RAG, design agent memory and organizational context management, compose multi-agent workflows, integrate tools and data, and build evaluations and release-quality gates. You will deploy and operate solutions on public cloud with strong SDLC, security, resiliency, and observability practices, partnering with product and business teams across CIB and Payments. You will also serve as a subject matter expert and contribute to the engineering community by advocating firmwide frameworks, tools, and software development practices.

Requirements

Formal training or certification in software engineering concepts and at least 5 years of applied experience, including at least 4 years working on AI/ML solutions.
Hands-on practical experience delivering system design, application development, testing, and operational stability.
Advanced proficiency in one or more programming languages, with strong Python skills and deep knowledge of data structures, algorithms, machine learning, data mining, information retrieval, and statistics.
Hands-on experience building LLM-powered or agentic applications in production, including tracing, evaluations, and guardrails.
Deep proficiency with Kubernetes and Amazon EKS, micro-VM isolation (such as Firecracker, Kata Containers, or gVisor), and sidecar architectures.
Proven experience designing defense in depth across network and mTLS, workload identity, fine-grained authorization, runtime isolation for untrusted or adversarial workloads, and application-level guardrails.
Practical RAG experience, including retrieval quality, embeddings, and vector stores.
Expert knowledge of at least one of AWS, Azure, or Kubernetes.
Knowledge of data management and data model design, and real-time processing using SQL (such as Postgres) and NoSQL stores (such as OpenSearch or Redis).
Excellent communication skills and the ability to partner effectively with senior technical and business stakeholders.
Proficiency in all aspects of the Software Development Life Cycle.
Advanced understanding of agile methodologies, including CI/CD, application resiliency, and security.
In-depth knowledge of the financial services industry and its IT systems.

Nice To Haves

MS in Computer Science, Statistics, Mathematics, Machine Learning, or a related field, or equivalent experience.
Experience with agent frameworks or runtimes, A2A, or MCP.
Experience with agent memory design, including memory nodes and episodic or semantic memory, and organizational context management.
Knowledge of knowledge graphs and graph databases used for retrieval; Graph RAG experience is a strong plus.
Understanding of LLM fine-tuning and small language model inference.
Ability to develop full-stack products using modern JavaScript/TypeScript frameworks such as Next.js or Svelte for agent UIs, including AG-UI or NEO UI SDK.
Experience in the financial or payments domain at a large institution, such as Investment Banking, Markets, Securities Services, or an adjacent area.
Knowledge of high-performance languages such as Go or Rust.

Responsibilities

Provide technical guidance and direction to support the business and its technical teams, contractors, and vendors.
Design and ship production agents on NEO across the federated portfolio, owning them from prototype through production.
Build production-grade retrieval using Graph RAG, knowledge-graph traversal, vector search, chunking, ranking, and grounding strategies.
Design agent memory, including episodic and semantic memory organized as memory nodes, with recall, summarization, and decay policies tuned to each use case.
Manage organizational context by assembling entitlement-, lineage-, and tenant-aware context so agents reason only over information they are allowed to access.
Compose multi-agent workflows using A2A and integrate tools and data through MCP servers, including Bitbucket, Confluence, Databricks, Kubernetes, Snowflake, and Splunk.
Build task-level and end-to-end agent evaluations, regression suites, LLM-as-judge processes, and quality and safety gates before release.
Deploy and operate solutions on AWS and/or Azure using strong SDLC, security, resiliency, and observability practices.
Partner with product and business stakeholders across CIB and Payments to turn use cases into shipped, supported agents.
Serve as a function-wide subject matter expert in one or more areas of focus.
Contribute to the engineering community by advocating firmwide frameworks, tools, and software development life-cycle practices.