Senior Generative AI Engineer

Senior Generative AI Engineer

New York, NY (Hybrid: 3 Days Per Week In Office)

Our client is a venture-backed Series A AI startup building the AI operating layer for wealth management. Their platform combines generative AI, agentic workflows, proprietary data, and enterprise-grade controls to help financial institutions automate complex processes, enhance advisor productivity, and deliver better client outcomes.
As they scale their engineering team, they are looking for a highly experienced Generative AI Engineer to help design, build, and deploy production-grade AI systems that will power the next generation of financial advisory tools.

As a Senior Generative AI Engineer, you will play a key role in building AI-native products and infrastructure from the ground up. You will work across LLM applications, agent architectures, retrieval systems, orchestration frameworks, and scalable backend services.

This is an ideal opportunity for someone who has experience building and shipping AI products within a high-growth startup or leading technology company and is excited by the challenge of building category-defining AI solutions in a fast-paced environment.

Key Responsibilities

• Design and deploy production-ready Generative AI applications and services
• Build multi-agent and agentic workflow systems capable of reasoning, planning, and tool execution
• Develop Retrieval-Augmented Generation (RAG) systems leveraging structured and unstructured data sources
• Implement memory, context management, and state persistence for AI-driven workflows
• Design scalable orchestration and execution frameworks for LLM-powered applications
• Build evaluation frameworks to measure model quality, accuracy, grounding, and reliability
• Develop observability, monitoring, and alerting capabilities for AI systems in production
• Collaborate with Product, Design, and Engineering teams to translate business requirements into scalable AI solutions
• Optimize AI systems for performance, reliability, latency, and cost efficiency
• Contribute to architecture decisions across model serving, vector databases, caching, and AI infrastructure

Required Qualifications

• 7+ years of software engineering experience with a strong focus on AI/ML systems
• Proven experience building and deploying LLM-powered applications in production environments
• Strong Python engineering skills with experience building scalable backend services
• Experience with:
  • Large Language Models (LLMs)
  • Retrieval-Augmented Generation (RAG)
  • Tool Calling & Function Calling
  • Structured Outputs
  • Prompt Engineering
  • AI Evaluation Frameworks
  • Workflow Orchestration
• Strong understanding of distributed systems and cloud platforms (AWS, Azure, or GCP)
• Experience designing robust, production-grade systems with monitoring and fault tolerance
• Strong problem-solving and system design capabilities

Preferred Qualifications

• Experience building multi-agent systems and autonomous workflows
• Hands-on experience with frameworks such as LangGraph, AutoGen, CrewAI, Semantic Kernel, or similar
• Experience with vector databases including Pinecone, Weaviate, Qdrant, or pgvector
• Knowledge of knowledge graphs, semantic search, or advanced retrieval architectures
• Background in financial services, fintech, or regulated environments
• Experience working within high-growth startups or rapidly scaling engineering organizations