Description

You're ready to gain the skills and experience needed to grow within your role and advance your career - and we have the perfect software engineering opportunity for you.

As a Software Engineer II at JPMorgan Chase within the Employee Platforms team, you are part of an agile team that works to enhance, design, and deliver the software components of the firm's state-of-the-art technology products in a secure, stable, and scalable way. As an emerging member of a software engineering team, you're at the forefront of delivering AI‑enabled software solutions. Join us as a valued member of a top‑performing team. As a Software Engineer II at JPMorgan Chase, you'll help design, build, and operate AI/ML applications with a focus on Generative and Agentic AI, working across backend, frontend, and AWS cloud.

Job responsibilities

• Implement production‑grade Generative AI and agent workflows on AWS, including tool use, planning, and memory
• Build secure, scalable microservices and RESTful APIs; integrate AI/ML with Java and Python services
• Develop modern web UIs with React or Angular to expose AI capabilities
• Contribute across the lifecycle: data preparation, model development, deployment, and monitoring
• Add automated tests and observability; apply security and performance best practices
• Collaborate with engineering, product, and data science to deliver reliable, compliant solutions
• Design and operate RAG pipelines with embeddings and vector stores; tune retrieval quality
• Implement guardrails and safety for PII redaction, content moderation, and prompt‑injection defenses
• Measure quality with offline and online evaluations; define metrics and run A/B experiments
• Optimize cost and latency for model inference, data pipelines, and API throughput
• Document architectures, APIs, and runbooks; share knowledge and support on‑call readiness

Required qualifications, capabilities, and skills

• Formal training or certification on infrastructure disciplines concepts and 3 plus years applied experience
• Build front‑end applications with React or Angular (TypeScript), using component‑based design and state management
• Apply LLMs and agentic patterns (tool calling, planning, memory), prompt engineering, RAG, embeddings/vector search, guardrails, and model evaluation
• Adapt and integrate foundation models and services into production applications
• Program in Python 3 for AI/ML: preprocess data, engineer features, train and evaluate models, and serve models
• Build cloud‑native AI applications and microservices on AWS using core services
• Design and integrate RESTful APIs and web services with FastAPI or Spring Boot
• Work with vector databases and implement RAG; manage Oracle or PostgreSQL with ORM frameworks such as JPA and Spring Data
• Write and maintain automated tests using JUnit, Mockito or PowerMockito, Spring Test, and PyTest
• Apply secure coding, identity, and data protection practices for AI workloads
• Communicate clearly and collaborate effectively with cross‑functional stakeholders
• Deliver production systems with observability and monitoring for reliability and performance

Preferred qualifications, capabilities, and skills

• Develop Java microservices with Spring Boot, Spring MVC, and Spring Security; apply domain‑driven design concepts
• Implement CI/CD and MLOps pipelines; containerize and orchestrate services with Docker or Kubernetes
• Leverage Terraform, GraphQL or gRPC, Kafka or SQS or Pub/Sub, Redis or Memcached, and observability tools such as OpenTelemetry, Datadog, or Grafana; apply MCP; operate in GCP where needed