Lead Generative AI Developer

Overview

Lead a hands-on effort to architect, build, and operationalize enterprise Generative AI and Large Language Model (LLM) solutions for COO Technology in New York.

What you'll do

• Design and implement end-to-end Generative AI pipelines (LLM integrations, RAG systems, autonomous AI agents, prompt engineering frameworks).
• Develop production-ready Python services and APIs for AI-driven features across COO platforms.
• Evaluate, integrate, and fine-tune LLMs and embedding models for domain-specific financial use cases.
• Build and maintain ML/GenAI deployment pipelines with MLOps practices, including reliability, observability, and governance.
• Design multi-agent orchestration frameworks for complex, multi-step operational workflows.
• Collaborate with AI Risk and Compliance teams to align solutions with regulatory and responsible AI requirements and data privacy standards.
• Design and optimize data pipelines for AI systems using vector databases and enterprise data platforms.

What you'll need

• 10+ years of professional software engineering experience, with at least 2+ years in Generative AI/LLM application development.
• Expert-level Python proficiency including async programming and API development (FastAPI, Flask).
• Deep hands-on experience with LLM frameworks including LangChain, LangGraph, and LlamaIndex.
• Hands-on experience with Google Cloud AI Platform.
• Proven experience with RAG architectures, embedding pipelines, and vector search.
• Strong understanding of prompt engineering and few-shot learning.
• Experience integrating with LLM APIs such as OpenAI, Azure OpenAI, Anthropic, AWS Bedrock, or Google Vertex AI.

Details

• Role is full time.
• Primary location: New York, New York, United States.