About CookUnity

Food has lost its soul to modern convenience. And with it, has lost the power to nourish, inspire, and connect us. So in 2018, CookUnity was founded as the first-of-its-kind platform that connects the world with the source of truly great food: chefs. Today, CookUnity delivers 50 million meals a year from the industry’s best chefs to homes all over the country. Fresh. Ready-to-eat. And crafted with the passion that nourishes body and soul.

Unwilling to stop there, CookUnity is expanding beyond delivery to become an ever-innovating marketplace focused on our singular mission: empower Chefs to nourish the world.

If that mission has you hungry in more ways than one, you’ve found the right job posting.

The Role

We are seeking a Staff AI Engineer, Agent Orchestration to lead the development of next-generation agentic systems that infuse Generative AI into every layer of the software delivery lifecycle. This is a hybrid role that blends full-stack engineering (Kotlin + TypeScript) with LLM systems design, focused on transforming developer workflows, CI/CD pipelines, observability, and runtime operations through AI-native automation.

As a technical spearheader, you will be responsible for architecting and scaling intelligent developer tools, copilots, and runtime agents that extend far beyond prompt engineering—enabling an accelerated, self-healing, and insight-driven engineering ecosystem.

Responsibilities

• Architect and deliver full-stack GenAI-integrated systems, leveraging Kotlin (Ktor/Spring), Python, React/TypeScript, and AWS tooling.
• Operationalize LLMs and agent frameworks to automate SDLC stages: from requirements parsing and code generation to test synthesis, deployment validations, and post-deploy analytics.
• Develop multi-agent orchestration patterns (e.g., tool use, planning, memory) across backend and frontend development flows.
• Embed GenAI-driven workflows into developer tooling: Full Test Driven Development cycle, PR summarization, AI-assisted code reviews, and contextual documentation retrieval.
• Extend CI/CD systems with LLM-based capabilities: dependency change impact prediction, and build-time telemetry analysis.
• Instrument systems with DataDog and AI-native observability: anomaly detection, root cause localization, and natural language log exploration.
• Partner cross-functionally with product, infra, and data teams to identify and prioritize AI-native engineering opportunities.
• Scout, evaluate, and hands-on integrate cutting-edge GenAI frameworks and developer tooling—bringing innovative capabilities into our stack to radically streamline coding, testing, and deployment workflows.
• Contribute to engineering-wide technical direction through architecture reviews, RFCs, and mentorship.

Requirements

• 7+ years of designing and building distributed back-end services in Kotlin (or Java) and modern TypeScript-based front-ends (React/Next.js).
• Ability to ship robust, production-grade Python code—owning everything from design and performance tuning to deployment.
• Proven track record shipping LLM/GenAI features to production, with experience across the lifecycle: prompt engineering, fine-tuning, latency optimization, evaluation, and safety alignment.
• Deep fluency with modern software delivery practices: test strategy, blue-green and canary deployments, observability, and rollback mechanisms.
• Demonstrated experience driving adoption of automated testing strategies (TDD/BDD) and CI/CD best practices.
• Strong written and verbal communication skills; ability to synthesize complex trade-offs for both technical and cross-functional stakeholders.

Preferred requirements:

• Strong full-stack development experience with Kotlin and React.
• Experience building and deploying multi-agent LLM systems with memory, reasoning, or dynamic planning.
• Familiarity with RAG pipelines, vector search, embeddings, and semantic caching.
• Prior experience in a high-growth, product-centric startup environment.

Where You'll Be:

• We offer you the flexibility to work where you work best!
• This team operates within the Eastern Standard time zone for collaboration.

Responsibilities:

• Leadership & Team Management:
  • Lead, mentor, and develop a cross-functional AI/ML team, including data engineers and embedded data engineers.
  • Foster a community-driven culture that encourages knowledge sharing, collaboration, and continuous learning.
  • Align team objectives with broader company