Site Reliability Engineer III
- Location
- Jersey City, NJ
- Work type
- Full Time · On-site
- Posted
- 2026-09-03
Job description
We are seeking a Generative AI Software Engineer to join our dynamic team supporting Bank of America Global Markets AI initiatives. The ideal candidate will have strong experience in Python, MLOps, RAG architecture, and full-stack/API development and a proven ability to design, build, and operationalize secure, scalable, and compliant GenAI platforms and reusable tooling.
Responsibilities:
Design, build, and maintain reusable tools and frameworks for Generative AI and Retrieval-Augmented Generation.
Develop secure, scalable, and high-performance services that meet functional, non-functional, and compliance requirements.
Implement RAG pipelines including chunking, embeddings, retrieval, reranking, and summarization.
Build API-based applications with FastAPI, JWT integration, and API Gateway patterns.
Engineer inference platforms using open-source toolsets, including AI gateway, policy store, and observability for RAG and related use cases.
Develop utilities, automation frameworks, and shared data science platforms for AI/ML and GenAI teams.
Collaborate in large teams using multi-repo workflows, IDE-based development, CI/CD, and continuous testing.
Drive process adherence, quality, and experimentation across the development lifecycle.
Troubleshoot and resolve complex infrastructure and platform issues with root-cause analysis.