Applied AI ML Lead - Machine Learning Engineer - Agentic Commerce
JPMorgan Chase14 hours ago
London, United KingdomStaff+
Responsibilities
- Design and ship production agents on NEO, owning them from prototype through production.
- Build retrieval systems using Graph RAG, knowledge-graph traversal, vector search, chunking, ranking, embeddings, and grounding strategies.
- Design agent memory with episodic and semantic memory nodes, recall, summarization, and decay policies.
- Assemble entitlement-, lineage-, and tenant-aware organizational context for secure agent reasoning.
- Compose multi-agent workflows with 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 systems, and quality and safety gates.
- Deploy and operate solutions on AWS and/or Azure with security, resiliency, observability, and SDLC practices.
- Partner with product and business teams to convert use cases into shipped and supported agents.
- Build traditional ML model-training pipelines using MLOps practices and develop batch and online inference.
- Collaborate with business, product, data science, and engineering teams across CIB sub-LOBs and Payments.
Requirements
- Master’s degree in Computer Science, Statistics, Mathematics, Machine Learning, or a related field, or equivalent experience.
- Hands-on production experience building LLM-powered or agentic applications, including tracing, evaluations, and guardrails.
- Strong Python programming skills and deep knowledge of data structures, algorithms, machine learning, data mining, information retrieval, and statistics.
- Knowledge of Kubernetes, including AWS EKS.
- Experience training models in Databricks and SageMaker and working with MLflow.
- Practical RAG experience involving retrieval quality, embeddings, and vector stores; Graph RAG experience is preferred.
- Expertise in at least one of AWS, Azure, or Kubernetes.
- Knowledge of data management and data model design, including real-time SQL processing and NoSQL stores such as PostgreSQL, OpenSearch, and Redis.
- Experience with agent frameworks or runtimes, A2A, or MCP is preferred.
- Experience designing agent memory, managing organizational context, and using knowledge graphs or graph databases for retrieval is preferred.
- Understanding of LLM fine-tuning and small language model inference is preferred.
- Ability to develop full-stack agent products using JavaScript or TypeScript frameworks such as Next.js and Svelte is preferred.
- Strong communication skills and ability to partner with senior technical and business stakeholders.
- Financial-services or payments experience at a large institution is preferred.
Benefits
- Career growth opportunities, exposure to cutting-edge platforms, and the opportunity to build impactful AI solutions in a regulated and secure environment.
- Equal opportunity employer with reasonable accommodations for religious practices, mental health needs, and physical disabilities.
Tech Stack
AWSAzureDatabricksJavaScriptKubernetesMLflowNext.jsPostgreSQLPythonRedisSnowflakeSplunkSQLSvelteTypeScript
Categories
About JPMorgan Chase
JPMorgan Chase provides consumer and commercial banking, payments, credit card, wealth management, and corporate and investment banking services to individuals, businesses, institutions, and governments. The public company (NYSE: JPM) earns revenue from interest, fees, trading, and asset management across operations in more than 100 markets. Headquartered in New York City with roots dating to 1799, it serves retail customers and prominent corporate and government clients through brands including Chase and J.P. Morgan.