AI/ML Engineer

Role Overview

Greenlight is hiring an AI/ML Engineer to join its AI team. You will design, build, and ship production Generative AI applications, AI agents, and ML systems for both customer-facing and internal products.

Responsibilities

• Design, build, and deploy production AI agents and multi-agent orchestration systems using:
  • prompt engineering
  • LLM chaining
  • tool-calling patterns
• Architect RAG pipelines with vector search, hybrid retrieval, and knowledge base management for question answering and decision support.
• Integrate third-party AI platforms/LLM providers, including:
  • authentication flows
  • tool schemas
  • agent-to-backend communication
• Design AI agent security architectures, including token exchange, delegated access, and user verification flows for on-behalf-of actions.
• Build production microservices and APIs serving as orchestration layers/tool endpoints, using:
  • FastAPI, Flask, or Node.js
• Architect authentication and authorization for AI services (IdP integration, token validation, service-to-service auth).
• Deploy, monitor, and maintain ML models and AI agent endpoints on cloud ML platforms (Databricks, AWS SageMaker), including scaling and health management.
• Develop data ETL pipelines for feature engineering, transaction processing, and knowledge base ingestion.
• Create evaluation and monitoring frameworks for non-deterministic AI, including:
  • agent correctness testing
  • retrieval quality
  • alerting
• Write technical design docs, architecture diagrams, and API contracts; mentor junior/mid engineers.
• Lead architecture reviews and produce roadmaps; evaluate emerging AI technologies to guide team strategy.
• Collaborate cross-functionally with product, platform, security, and operations to define requirements and ship end-to-end AI integrations.

Requirements

• Extensive experience building and deploying AI agents and Generative AI in production.
• Deep knowledge of LLMs, agentic architectures, multi-agent systems, RAG, vector search, tool use/function calling, prompt engineering, and fine-tuning.
• Hands-on experience with AI/ML frameworks such as LangChain, LangGraph, LlamaIndex, or equivalents.
• Strong software engineering skills building production microservices/APIs in Python or JavaScript/TypeScript.
• Experience designing auth systems for AI apps (OAuth, token-based access control, delegated authorization).
• Proficiency deploying/serving on a major cloud ML platform (Databricks, AWS SageMaker, or Google Vertex AI).
• Ability to produce clear technical documentation and architecture specs.
• Strong cross-functional communication and collaboration.

Preferred

• Experience with CI/CD.