Applied AI ML Lead
Research JPMorgan Chase before you apply
Check ratings, real-employee reviews, verified pay, and interview difficulty.
Promote design and delivery of agentic AI that improves Software quality, security and resilience in regulated settings
As an Applied AI ML Lead within JP Morgan Chase Asset & Wealth Management Technology, you will lead the design and delivery of agentic AI solutions that improve software quality, security, and resiliency in a regulated environment. You will build and scale autonomous agents that detect and auto-remediate code and infrastructure definitions that fall short of well‑architected principles and firm engineering governance standards spanning the inner loop (IDE-time) and the outer loop (CI/CD pipeline-time compensating controls that prevent non-compliant changes from reaching production).
Job responsibilities
- Own end-to-end technical direction for agentic capabilities: architecture, delivery plan, reliability, security, and adoption.
- Design and implement LLM-driven agents for code generation/refactoring, standards conformance, test creation, documentation updates, release readiness checks, and operational insights.
- Establish safe “auto-heal” patterns: diff/PR-based remediation, risk-tiered actions, human-in-the-loop approvals, and explainable decisions.
- Build orchestration and coordination for multi-agent workflows (e.g., LangGraph / AutoGen or similar): state management, tool-calling, structured outputs, and guardrails.
- Implement outer-loop pipeline agent stages as compensating controls: policy checks, risk scoring, exception routing, evidence collection, and release gating.
- Define and run a rigorous evaluation program: regression suites, golden datasets, adversarial testing, prompt/model versioning, rollout controls, and continuous monitoring.
- Partner with governance, security, platform engineering, and application teams to translate standards into enforceable automation and measurable outcomes.
- Mentor and raise the bar for engineering quality through design reviews, coaching, and setting team best practices.
Required qualifications, capabilities, and skills
Formal training or certification on software engineering concepts and 5+ years applied experience
- Significant software engineering experience with proven technical leadership delivering production systems at scale.
- Demonstrated experience building/shipping LLM-enabled applications (agents/tool use, structured outputs/validation, grounding/RAG, observability).
- Strong SDLC understanding across IDE/inner loop, PR workflows, and CI/CD/outer loop in regulated environments.
- Security-first engineering mindset: least privilege, secrets hygiene, auditability/traceability, change controls, and secure-by-design automation.
- Excellent stakeholder communication; ability to drive alignment across engineering, product, security, and governance.
Preferred qualifications, capabilities, and skills
- Python (FastAPI/Pydantic) and strong distributed systems/reliability background.
- Experience building automated remediation (codemods/refactoring tools) and policy/guardrail systems with explain ability.
- Strong observability discipline (logs/metrics/tracing; OpenTelemetry and common monitoring platforms).