Software Engineer III -AI/ML

We have an exciting and rewarding opportunity for you to take your software engineering career to the next level. 

As a Software Engineer III at JPMorganChase within the Commercial & Investment Bank, you serve as a seasoned member of an agile team to design and deliver trusted market-leading technology products in a secure, stable, and scalable way. You are responsible for carrying out critical technology solutions across multiple technical areas within various business functions in support of the firm’s business objectives.

Job responsibilities

• Executes software solutions across design, development, testing, and technical troubleshooting for AI/ML and agentic systems, thinking beyond conventional approaches to decompose problems into agent plans, tools, Skills, and workflows.
• Builds and maintains secure, high-quality production code for agent runtimes and services, including prompt/tool orchestration, state management, memory patterns, routing, and fallback strategies.
• Produces architecture and design artifacts for complex applications (e.g., multi-agent systems, Agentic RAG pipelines, evaluation harnesses) and remains accountable for ensuring design constraints are met in implementation.
• Develops Agentic RAG solutions: ingestion, chunking/indexing, embedding strategies, retrieval/reranking, citations/attribution patterns, and grounding + hallucination mitigations.
• Leverages enterprise-authorized AI coding assist tools within the work environment to improve code quality, delivery speed, and productivity across complex deliverables (e.g., code generation/refactoring, unit test creation, documentation), while validating outputs through peer review, automated testing, and secure coding standards; contributes learnings and reusable patterns to improve broader team effectiveness.
• Applies knowledge of tools within the Software Development Life Cycle toolchain, including enterprise-authorized AI-assisted development and automation capabilities, to improve the value realized by automation.
• Integrates agents with enterprise systems via APIs and tool interfaces, including MCP-based connectors, ensuring least privilege, auditability, and safe action execution.
• Gathers, analyzes, and synthesizes insights from large, diverse datasets to build AI features, telemetry, and dashboards for quality, drift, latency, reliability, and cost. Implements model/agent evaluations (offline + online): golden sets, regression testing, adversarial testing, safety testing, and human-in-the-loop review flows.
• Proactively identifies hidden problems and patterns in data and system behavior; uses insights to improve coding hygiene, prompt/tool hygiene, retrieval quality, and system architecture. Contributes to software engineering communities of practice exploring emerging AI/ML tooling (e.g., agent frameworks, vector databases, inference optimization, fine-tuning, distillation, model routing).
• Adds to team culture of diversity, opportunity, inclusion, and respect

Required qualifications, capabilities, and skills

• Formal training or certification on software engineering concepts and 3+ years applied experience
• Hands-on experience using enterprise-authorized AI-assisted software development tools within the work environment (e.g., for coding, test creation, troubleshooting, or documentation) with demonstrated ability to critically evaluate, validate, and refine AI-generated outputs for correctness, performance, and security.
• Understanding of responsible AI use in engineering workflows, including data sensitivity considerations, secure handling of inputs/outputs, and adherence to resiliency and security expectations; ability to guide peers on safe and effective usage within team practices.
• Proficient in coding in one or more languages (e.g., Python, Java, TypeScript/Node.js, Go).
• Experience developing, debugging, and maintaining code in a large corporate environment, including API design, distributed systems patterns, and database/querying languages.
• Strong knowledge of the Software Development Life Cycle, with emphasis on MLOps/LLMOps practices (CI/CD for models/agents, versioning, reproducibility, release controls).
• Solid understanding of agile methodologies and engineering excellence practices such as CI/CD, resiliency, security, observability, and incident management.
• Demonstrated knowledge in at least one technical discipline such as AI/ML, LLMs, agent orchestration, retrieval systems, cloud, or data engineering.
• Working knowledge of Agentic RAG concepts (retrieval, grounding, ranking, evaluation) and tool/function calling patterns for AI agents.

Preferred qualifications, capabilities, and skills

• Familiarity with MCP (Model Context Protocol) concepts and/or building standardized tool interfaces for agents. Familiarity with responsible AI practices: guardrails, policy-based controls, privacy/security-by-design, red teaming, and safe automation.
• Experience with modern front-end technologies to build agent experiences (chat/assistants, workflow UIs, evaluation UIs).
• Exposure to cloud technologies and patterns for AI systems (e.g., containerization, Kubernetes, serverless, managed ML services, secrets management).
• Experience with vector databases/search, document processing pipelines, and unstructured data tooling. Experience with model performance tuning (latency/cost), inference optimization, and/or model routing strategies.