Software Engineer III - AI/ML Engineer
Salary not listed • Jersey City, NJ, United States • Full-time
Posted 15d ago
No salary is listed. Many US states require employers to post a pay range, so ask about pay early.
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
JPMorgan Chase is seeking a Software Engineer III within Corporate Technology to design and deliver agentic AI platforms and large language model-enabled services for Finance use cases. This role involves contributing to technical design, building cloud-native services on AWS, and enhancing system quality through evaluation and observability. You will also play a key part in raising engineering standards through robust code reviews, documentation, and cross-team collaboration.
Responsibilities
- Design and implement scalable, reliable agentic AI platform components for enterprise workflows.
- Build production-grade AI systems including agents, skills, memory patterns, guardrails, and tool-use orchestration.
- Implement retrieval and context-engineering patterns such as embeddings, semantic search, grounding, summarization, and prompt/version management.
- Engineer cloud-native services on AWS using containers, serverless compute, and event-driven messaging.
- Optimize latency, throughput, scalability, caching, context efficiency, and cost for large language model workloads.
- Develop secure, reusable APIs and integrations connecting AI capabilities to enterprise platforms.
- Implement evaluation, experimentation, regression testing, and observability for AI system quality and behavior.
- Partner with product, platform, and engineering teams to translate requirements into deliverables.
- Contribute to technical standards and code quality through design reviews, documentation, and peer code reviews.
- Leverage enterprise-authorized AI coding assist tools to improve code quality and delivery speed, validating outputs through review and testing.
- Apply knowledge of the Software Development Life Cycle toolchain, including AI-assisted development, to enhance automation value.
Requirements
- 3+ years of applied experience in software engineering concepts, with formal training or certification.
- Hands-on experience building and operating production large language model applications, including agentic patterns and tool integrations.
- Strong software engineering fundamentals with experience delivering cloud-native services using containers and serverless designs on AWS.
- Advanced Python programming skills with experience writing production-quality code.
- Experience with retrieval-augmented generation (RAG) approaches, including embeddings and semantic search, and practical context engineering.
- Proficiency in building React-based front-end experiences that integrate backend APIs, with attention to reliability, security, and performance.
- Experience establishing or contributing to evaluation, testing, and monitoring practices for AI system quality and reliability.
- Ability to troubleshoot complex issues across distributed systems, including asynchronous workflows and event-driven architecture.
- Strong collaboration and communication skills for technical decisions and trade-offs.
- Hands-on experience using enterprise-authorized AI-assisted software development tools, with ability to critically evaluate and refine AI-generated outputs.
- Understanding of responsible AI use in engineering workflows, including data sensitivity, secure handling, and adherence to resiliency and security expectations.