Lead Software Engineer and ML Engineer - Sales Copilot

JPMorgan Chase & Co.•Jersey City, NJ

1d•$156,750 - $215,000

About The Position

As a Lead Software Engineer at JPMorganChase within the Commercial and Investment bank Digital & Platform Services, Data Analytics, 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. As a core technical contributor, you are responsible for conducting critical technology solutions across multiple technical areas within various business functions in support of the firm’s business objectives. JPMorganChase is hiring top talent to join the growing Commercial & Investment Bank Technology organization within Digital & Platform Services / Data Analytics, building production AI agents on NEO that leverage the firm’s scale, data, and full-service advantage to deliver measurable impact across the Commercial & Investment Bank and Payments. As a Senior AI Application Engineer, you’ll design, productionize, and operate LLM-powered agents on NEO (the firm’s agent runtime PaaS on AWS/Azure), partnering closely with business, product, and engineering teams in a fast-paced environment.

Requirements

Formal training or certification on software engineering concepts and 5+ years applied experience with at least 4 years working on AI/ML solutions.
Hands-on practical experience delivering system design, application development, testing, and operational stability
Advanced in one or more programming language(s) - Strong programming skills in Python, with 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 (e.g., Firecracker, Kata Containers, gVisor), and sidecar architectures, with proven experience designing defense in depth across the stack: network and mTLS, workload identity, fine-grained authorization, runtime isolation for untrusted or adversarial workloads, and application-level guardrails
Practical RAG experience — retrieval quality, embeddings, and vector stores; Expert knowledge of at least one of: AWS, Azure, Kubernetes.
Knowledge of data management and data model design; real-time processing using both SQL (e.g., Postgres) and NoSQL stores (e.g., OpenSearch, Redis).
Excellent communication skills with the ability to partner effectively with senior technical and business stakeholders.
Proficient 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 their IT systems

Nice To Haves

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

Responsibilities

Design and ship production agents on NEO across the federated portfolio, owning them from prototype through production.
Build retrieval that holds up in production: Graph RAG combining knowledge-graph traversal with vector search, plus chunking, ranking, and grounding strategies that keep answers accurate and auditable.
Design agent memory: episodic and semantic memory organized as memory nodes, with recall, summarization, and decay policies tuned per use case.
Own organizational context management — assembling entitlement-, lineage-, and tenant-aware context so each agent reasons over only what it’s allowed to see.
Compose multi-agent workflows using A2A, and integrate tools and data through MCP servers (Bitbucket, Confluence, Databricks, Kubernetes, Snowflake, Splunk).
Build and run evals: task-level and end-to-end agent evaluations, regression suites, LLM-as-judge, and quality/safety gating before release.
Deploy and operate solutions on public cloud (AWS and, or Azure) with strong SDLC, security, resiliency, and observability practices.
Partner with product and business partners across CIB and Payments to turn use cases into shipped, supported agents.
Leads evaluation sessions with external vendors, startups, and internal teams to drive outcomes-oriented probing of architectural designs, technical credentials, and applicability for use within existing systems and information architecture