Senior AI Engineer - Model Selection and Orchestration

The role

You will design and build the decision and orchestration layer that helps AI agents choose how to handle a task, such as using deterministic logic, retrieval, a model, or a tool call. You will write production code, evaluate AI system behavior, and integrate models and tools within the AI Platforms team at Zip.

What you will do

• Design and implement the decision layer that determines how an agent responds to a task, including when to escalate to a human.
• Develop intent classification and clarification flows that distinguish information requests from actions.
• Benchmark rules, retrieval, classifiers, smaller models, and reasoning models on quality, latency, safety, and cost.
• Implement model adapters, routing logic, structured outputs, timeouts, retries, and fallback behavior.
• Connect agents to approved APIs and tools with authentication, authorization, policy checks, and customer confirmation.
• Partner with Security and Risk on input and output protections, sensitive-data handling, and prompt-injection defenses.
• Build reusable AI platform capabilities such as orchestration patterns, model adapters, and routing components.
• Monitor AI systems in production and improve model selection and orchestration using production evidence.
• Use AI-assisted development tools in your engineering workflow and evaluate their output for correctness and security.

Required qualifications

• Minimum of 10 years of related experience with a Bachelor's degree; or 6 years and a Master's degree; or a PhD with 3 years experience; or equivalent experience.
• 10+ years of professional experience building, testing, deploying, and operating production software, including AI or ML-enabled applications beyond prototypes.
• Strong experience with Python or TypeScript and modern software engineering practices.
• Practical experience with LLM tool calling, structured outputs, retrieval-augmented generation, and agent or workflow orchestration.
• Ability to evaluate classification quality, uncertainty, fallback strategies, and model approaches using task success, latency, reliability, and inference cost.
• Experience with cloud deployment, automated testing, CI/CD, observability, identity and access controls, secrets management, retries, idempotency, and failure recovery.
• Strong judgment on when to use deterministic software, retrieval, a model, or a combination, and when an agent should ask for clarification or hand off to a person.
• Ability to deliver complex technical work independently within shared architecture standards and communicate tradeoffs clearly.
• Hands-on experience using AI-assisted development tools in day-to-day engineering work.

Nice to have

• Experience with Google Cloud, Google ADK, Model Garden, or equivalent managed AI platforms.
• Experience with semantic routing, open-weight models, Model Context Protocol (MCP), reusable agent-development frameworks, or Azure integrations.
• Experience with payments, fintech, or other environments where correctness, auditability, and controlled access are essential.

Benefits

• Flexible working culture and incentive programs
• Unlimited PTO
• Generous paid parental leave and family support policies
• Company-sponsored 401k match
• Learning and wellness subscription stipend
• Employer-sponsored insurance for you and your dependents, with several 100% Zip-covered choices
• Union Square office with a casual dress code

Before you apply

• Zip participates in the federal government's E-Verify program.

About the company

Zip is a global Buy Now, Pay Later company that gives millions of customers simpler and fairer ways to pay. Its core markets are the US and ANZ, with merchant partners including Amazon, Best Buy, eBay and Uber.