Lead Machine Learning Engineer - Agentic Pricing

Build production AI agents at JPMorganChase within the Corporate & Investment Bank Technology organization. You will work on the NEO agent runtime platform on AWS and Azure, designing, productionizing, and operating LLM-powered agents that support use cases across the Corporate & Investment Bank and Payments.

NEO already runs a federated portfolio of production agents, including forecasting, anomaly detection, and log analysis, with additional capabilities such as sales fulfillment and voice-of-client close behind. In this role, you will extend the platform by shipping new production agents and strengthening the underlying retrieval, memory, evaluation, and governance patterns.

What you’ll do

• Design and ship production agents on NEO across the federated portfolio, owning work from prototype through production.
• Build production-ready retrieval including chunking, ranking, and grounding strategies to keep answers accurate and auditable.
• Design agent memory with episodic and semantic memory organized as memory nodes, including recall, summarization, and decay policies tuned per use case.
• Own organizational context management so each agent reasons over only permitted information using entitlement-, lineage-, and tenant-aware context.
• Compose multi-agent workflows using A2A, and integrate tools and data through MCP servers (Bitbucket, Confluence, Databricks, Kubernetes, Snowflake, Splunk).
• Build and run evaluations including task-level and end-to-end agent evaluations, regression suites, LLM-as-judge, and quality/safety gating before release.
• Deploy and operate solutions on AWS and/or Azure using strong SDLC, security, resiliency, and observability practices.
• Partner with product and business teams across the Corporate & Investment Bank and Payments to turn use cases into shipped, supported agents.

What you bring

• MS in Computer Science, Statistics, Mathematics, Machine Learning, or related field (or equivalent experience).
• 7+ years of development experience, with at least 4 years working on AI/ML solutions.
• Hands-on experience building LLM-powered or agentic applications in production, including tracing, evaluations, and guardrails.
• Strong programming skills in Python, with deep knowledge of data structures, algorithms, machine learning, data mining, information retrieval, and statistics.
• Practical RAG experience, including retrieval quality, embeddings, and vector stores.
• Expert knowledge of at least one: AWS, Azure, Kubernetes.
• Knowledge of data management and data model design; real-time processing using SQL (e.g., Postgres) and NoSQL stores (e.g., OpenSearch, Redis).
• Excellent communication skills with the ability to collaborate with senior technical and business stakeholders.

Preferred capabilities

• Graph RAG experience (combining knowledge-graph traversal with vector search).
• Experience with agent frameworks or runtimes, including A2A or MCP.
• Experience with agent memory design (memory nodes, episodic/semantic memory) and organizational context management.
• Knowledge of knowledge graphs and graph databases used for retrieval.
• Understanding of LLM fine-tuning and small language model inference.
• Ability to build full-stack products using modern JavaScript/TypeScript frameworks (e.g., Next.js, Svelte) for agent UIs (AG-UI / NEO UI SDK).
• Experience in 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.

Tools and technologies

NEO, AWS, Azure, Python, Databricks, GenAI Gateway, MCP, Bitbucket, Confluence, Kubernetes, Snowflake, Splunk, SQL, Postgres, NoSQL, OpenSearch, Redis, A2A, LLM-as-judge, vector stores, embeddings, Graph RAG, knowledge graphs, graph databases, JavaScript, TypeScript, Next.js, Svelte, AG-UI, NEO UI SDK, Go, Rust.

Role details

Location: Jersey City, NJ (onsite)

Compensation: USD 171,000 - 260,000 per year