Greenlight Financial Technology is the leading family fintech company on a mission to help parents raise financially smart kids. They are seeking an AI/ML Engineer to design, build, and ship production Generative AI applications and ML systems, leading technical design and cross-functional collaboration to enhance AI capabilities across the organization.
Responsibilities:
- Design, build, and deploy production AI agents and multi-agent orchestration systems with prompt engineering, LLM chaining, and tool-calling patterns for complex, multi-step workflows
- Architect RAG pipelines with vector search, hybrid retrieval, and knowledge base management for AI-driven question-answering and decision-support
- Integrate third-party AI platforms and LLM providers, designing authentication flows, tool schemas, and agent-to-backend communication
- Design AI agent security architectures including token exchange, delegated access, and user verification flows for systems acting on behalf of users
- Build production microservices and APIs (FastAPI, Flask, Node.js) serving as orchestration layers and tool endpoints for AI agent systems
- Architect authentication and authorization for AI services: identity provider integration, token validation, and service-to-service auth
- Deploy, monitor, and maintain ML models and AI agent endpoints on cloud platforms (Databricks, AWS SageMaker) including scaling and health management
- Build data ETL pipelines for feature engineering, transaction processing, and knowledge base ingestion
- Develop evaluation and monitoring frameworks for non-deterministic AI systems: agent correctness testing, retrieval quality, and alerting
- Author technical design docs, architecture diagrams, and API contracts; mentor junior and mid-level engineers on AI development practices
- Lead architecture reviews and produce design documents with implementation roadmaps; evaluate emerging AI technologies to inform team strategy
- Collaborate cross-functionally with product, platform, security, and operations to define requirements, prioritize features, and ship AI integrations end-to-end
Requirements:
- Extensive experience building and deploying AI agents and Generative AI applications 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 equivalent
- Strong software engineering skills building production microservices and APIs in Python or JavaScript/TypeScript
- Experience designing auth systems for AI applications: OAuth, token-based access control, and delegated authorization
- Proficiency with a major cloud ML platform (Databricks, AWS SageMaker, or Google Vertex AI) for deployment and serving
- Ability to produce clear technical design documentation and architecture specs for complex systems
- Strong cross-functional communication and collaboration across product, engineering, security, and operations
- Experience with CI/CD pipelines and infrastructure tooling (GitHub Actions, Jenkins, Kubernetes, Terraform)
- Experience with a JVM language (Java, Kotlin, or Scala) for backend service development
- Background in data pipeline and streaming tools (Airflow, Spark)