Vice President, AI/ML Software Engineer
BNY Mellon3 months ago
Responsibilities
- Design and implement agentic AI pipelines with agent loops, tool registries, memory stores, reasoning traces, and self-correction mechanisms.
- Build end-to-end RAG systems covering document ingestion, OCR preprocessing, chunking, embeddings, vector indexing, hybrid retrieval, re-ranking, context assembly, and LLM generation.
- Develop vectorization pipelines, multi-agent coordination patterns, prompt engineering infrastructure, and automated evaluation harnesses.
- Build FastAPI production APIs for extraction, validation, and classification, and contribute to Java/Spring Boot platform services.
- Design database schemas for audit trails, pipeline runs, memory entries, and knowledge graphs, while implementing content policy and data governance controls.
- Mentor 2–3 mid-level engineers and participate in architecture reviews, design sessions, documentation, and technical collaboration with product and business stakeholders.
Requirements
- Bachelor’s degree in Computer Science, Engineering, or a related field; an advanced degree is preferred.
- At least 6 years of professional software engineering experience and at least 2 years building production AI/ML systems.
- Strong RAG expertise, including embedding models, vector databases, chunking, retrieval optimization, context-window management, and prompt assembly.
- Experience with agent orchestration, tool-use patterns, function calling, structured output parsing, memory and state management, and multi-turn agent interactions.
- Proficiency in Python, FastAPI, asynchronous programming, Pydantic, Poetry, and pytest.
- Experience with LLM integration, prompt engineering, token management, streaming, error handling, and rate limiting.
- Experience with NLP and document processing, including OCR post-processing, text segmentation, and entity extraction.
- Experience with unit and integration testing, golden-truth validation, retrieval metrics, API design, RESTful services, and OpenAPI specifications.
- Preferred qualifications include knowledge graph construction, code AI concepts, Java/Spring Boot, Angular/TypeScript, model evaluation, fine-tuning or prompt optimization, graph RAG, hybrid retrieval, capital markets or financial services, and enterprise deployment.
Benefits
- Competitive compensation, benefits, wellbeing programs, and pay-for-performance culture.
- Flexible global resources and tools supporting health, personal resilience, and financial goals.
- Generous paid leave, including paid volunteer time.
- Equal Employment Opportunity/Affirmative Action workplace.
- Position is located in New York, NY and is at-will.
Tech Stack
Categories