Software Engineer III - GenAI Patterns

JPMorgan Chase & Co.•Plano, TX

13h

About The Position

As a Software Engineer III at JPMorganChase within the Commercial and Investment Bank, you serve as a full-stack software engineer who’s passionate about building AI-powered solutions that perform reliably at enterprise scale. You’ll help shape and deliver production-grade platforms that blend strong software engineering with modern GenAI patterns—retrieval, knowledge libraries, embedding-based search pipelines, and validation frameworks—while operating in a high-compliance environment.

Requirements

Formal training or certification on software engineering concepts and 3+ years applied experience
Strong full-stack engineering fundamentals and a “build it right” mindset (clean APIs, robust services, thoughtful UX).
Experience building production systems: CI/CD, monitoring/alerting, incident hygiene, performance tuning, and scalability.
Familiarity with search and retrieval systems (semantic search, vector stores, indexing, ranking, query pipelines) and how they integrate into applications.
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.
Comfort working with LLM-based systems (prompting patterns, structured outputs, evaluation, and guardrails) in real-world environments.
A high learning mindset—curious, adaptable, and motivated to apply modern best practices thoughtfully rather than chasing hype.
Ability to collaborate across engineering, product, and risk/compliance partners to deliver safely and responsibly.

Nice To Haves

Knowledge of generative AI concepts., prompt engineering, RAG, embeddings, and vector search, LangChain
Knowledge of model evaluation, guardrails, hallucination reduction
Experience with Python, Java(spring boot),Open AI, Database(vector/pinecone), AWS
Knowledge on open source community contribution/start up experience is plus
Self motivation and Passion is the key driver

Responsibilities

Build and own end-to-end, full-stack features (UI, APIs, services, data layers) for AI-enabled products used at scale.
Design and implement knowledge library + retrieval (RAG) capabilities, including embedding generation, indexing strategies, and semantic search pipelines.
Develop AI content and document-generation solutions, with guardrails and auditability appropriate for regulated workflows.
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.
Engineer agentic workflows (tool-using/step-based systems) with robust agentic validations (policy checks, workflow constraints, and deterministic controls).
Implement semantic validations to improve output quality (grounding checks, relevance, duplication detection, hallucination-reduction patterns, and structured evaluation signals).
Stay current on industry trends in applied AI/ML systems and translate them into pragmatic, maintainable engineering decisions.
Raise the bar on engineering best practices: testing strategy, reliability, observability, performance, and secure coding patterns.