What are the responsibilities and job description for the Executive Director Principal Software Engineer - Agentic Engineering position at JPMorgan Chase?
If you are looking for a game-changing career, working for one of the world's leading financial institutions, you’ve come to the right place.
As the Principal Software Engineer at JPMorgan Chase within the Corporate and Investment Bank Technology – Securitized Product Group Technology team, you will lead the design, build, and scaling of our next-generation multi-agent AI platform. This is not a manage-from-a-distance role: you will write production code, own key architectural decisions, unblock engineers, and be accountable for production outcomes—while also setting multi-year strategy and building a high-performing team.
If you’ve built agentic systems in production (not prototypes), can distinguish orchestration vs. parallelization in real distributed environments, and can whiteboard with a CTO then land a PR the same afternoon—this role is for you
Job responsibilities
- Own the multi-year agentic platform strategy: agent toolchains, RAG pipelines, memory/state architectures, context management, evaluation, and feedback/reinforcement loops.
- Architect scalable multi-agent systems using LangChain, LangGraph, AutoGen, or equivalent frameworks—and define when to use simpler primitives.
- Design distributed ingestion and workflow systems (batch streaming) with data contracts, lineage, and strong data-quality patterns.
- Establish standards for the agentic development lifecycle: context engineering, automated evals, observability, security, and release readiness.
- Contribute directly in Python (services, concurrency, performance, reliability) and set the bar via reference implementations.
- Lead design and code reviews; engage directly in incident response and production hardening.
- Build reusable agent components: planning/decomposition, tool/function calling, self-critique/reflection loops, state management, multi-agent coordination, and safety controls.
- Partner with MLOps/platform on deployment, monitoring, and retraining pipelines (MLflow, SageMaker, Vertex AI, Azure ML, etc.).
Required qualifications, capabilities, and skills
- 10 years in software engineering, including 5 years leading senior technical teams and driving architecture for large systems.
- Expert Python; working proficiency in TypeScript, Go, or Rust.
- Deep familiarity with agentic frameworks (LangChain, LangGraph, AutoGen, or equivalent).
- Strong command of RAG, prompt/context design, tool/function calling, and multi-step reasoning patterns.
- Distributed systems and data platform experience: Kafka, Spark, gRPC/REST, Docker/Kubernetes.
- Cloud fluency (AWS/Azure/GCP) and MLOps tooling (MLflow, Kubeflow, SageMaker, Vertex AI).
- Familiarity with vector databases, knowledge graphs, and semantic retrieval patterns.
- Strong executive communication—able to align stakeholders on trade-offs, timelines, and risk.
- Platform mindset: builds durable systems, not fragile demos.
Preferred qualifications, capabilities, and skills
- kdb /q, ClickHouse, or other time-series/analytical data stores.
- Financial services domain (trading infrastructure, derivatives, fixed income).
- Publications, talks, or open-source contributions in agentic AI.
- Experience designing “agentic SDLC” / software-delivery automation.