AI Native Engineer

CookUnity; New York, Northern (NY, KY); Hybrid; USD 130,000 - 190,000; Full time

Benefits offered by this job

5-year Sabbatical: 4-week paid

Paid family leave

CookUnity credits for meals

Wellness perks & fitness subsidies

AI-forward workplace access to ChatGPT

Job summary

CookUnity is seeking an AI Engineer to redesign how work gets done by mapping end-to-end workflows, identifying automation opportunities, and building production tools. You will own automation in production, monitor KPIs, and continuously improve systems across a cross-functional team.

Join a fast-growing marketplace for chefs and meals, using agentic workflows and deterministic apps to drive efficiency, with strong emphasis on governance and safety.

Qualifications

• Experience building production-grade AI automation workflows.
• Ability to map business processes and redesign for automation.
• Familiar with APIs, CLIs, and data warehouses.

Responsibilities

• Map high-value workflows end-to-end and identify automation opportunities.
• Build production workflows and internal tools used daily.
• Own agents/apps in production with monitoring and KPIs.
• Evaluate model changes and data shifts to improve systems.

Skills

LLMs in production

TypeScript

Python

Kotlin

APIs

System integration

Tools

Braze

Ramp

NetSuite

Jira

Linear

Slack

Job description

Food has lost its soul to modern convenience. And with it, 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:

Every team at CookUnity has workflows that could be 10-100x more effective with the right automation. But unlocking that requires someone who can see the opportunity, design the future-state process, build it, and keep it running. That's this role.

You'll embed directly with the cross functional AI team as a dedicated AI engineer. Your job isn't to write code faster with AI. It's to fundamentally redesign how work gets done. You'll map existing workflows end-to-end, identify where throwing compute at a task creates step-change value, and then build the solution: sometimes that's an agent, sometimes it's a deterministic internal app, sometimes it's a combination. Knowing which to reach for, and when, is a core part of the job.

You'll architect the automated version, build it, and then own it in production: tracking KPIs, managing evals after model changes, and continuously improving.

This is equal parts business analyst, systems integrator, and engineer. You'll spend as much time interviewing stakeholders and mapping data flows as you will writing code. You need to be the kind of person who can sit with a team lead, whiteboard a procurement process or a campaign launch workflow, spot the bottleneck that's begging for automation, and have a working prototype by end of week.

You'll report to the Head of Applied AI.

Responsibilities:

Discover and Design

• Map the team's highest-value workflows end-to-end: structured and unstructured data flows, decision points, handoffs, and bottlenecks.
• Identify where automation can drive step-change outcomes: processing orders of magnitude more inputs, collapsing multi-day processes into hours, or enabling work that simply wasn't feasible before.
• Design the future-state workflow: where an agent acts autonomously, where a deterministic app handles the logic, where humans review, what context is needed, and what guardrails keep it safe.
• Build the business case. You can articulate why this workflow matters in terms of time saved, revenue impact, or cost reduced.

Build and Ship

• Build production workflows and internal tools that the team relies on daily, not just demos.
• Use your judgment on the right tool for the job: agentic workflows when tasks require reasoning and flexibility, deterministic apps and scripts when the logic is well-defined and reliability matters most.
• Work across the company's toolstack: APIs, CLIs, MCP servers, spreadsheets, data warehouses, workflow orchestration, databases, and whatever else needs connecting.
• Create human-in-the-loop interfaces where they matter. Knowing when to automate fully and when to keep a human checkpoint is a core skill.
• Write clean, maintainable code. You'll use AI tools to move fast, but you own the quality of what ships.

Run and Improve

• Own your agents and apps in production. Monitor performance, track KPIs, and explain outcomes to stakeholders.
• Manage evals and regression testing after model updates, prompt changes, or upstream data shifts.
• Continuously improve: every workflow you own should get measurably better over time.
• Build institutional knowledge: document patterns, create playbooks, and teach your team to think in terms of what's now automatable.
• Level up your team’s compute fluency and increase AI adoption.

What Success Looks Like

• Within 60 days, you've mapped 3 high value workflows and shipped your first production tool (agent or app) that the team uses daily.
• Within 6 months, you've automated or agent-assisted 3-5 core workflows with measurable impact on team throughput or cost.
• The team you've worked with considers you indispensable, not because you're the only one who can code, but because you see automation opportunities they can't.
• You can show a clear before/after: hours saved, error rates reduced, throughput increased, or entirely new capabilities unlocked.
• Your agents and apps are running reliably in production with monitoring, evals, and documented runbooks.
• Demonstrated ability to map a business process and redesign it with automation. This is the #1 skill. Show us a time you took a messy real-world workflow, understood it deeply, and made it dramatically better.
• Technical fluency to connect systems and build production workflows. You're comfortable with APIs, CLIs, MCP, databases, and workflow orchestration. You can wire up business systems without waiting for someone else to do it.
• Good judgment on agents vs. deterministic tools. You know when an LLM-powered agent is the right call and when a well-built internal app or script is better. You don't reach for AI when a cron job will do, and you don't build brittle rule engines when the task needs reasoning.
• Strong foundation in at least one programming language (TypeScript, Python, Kotlin or similar) and ability to build full-stack when needed.
• Hands-on experience with LLMs in production, not just prompting, but building reliable systems: structured outputs, eval frameworks, error handling, human-in-the-loop design.
• Operational maturity. You don't just build things, you run them. You monitor, measure, iterate, and document.
• Communication skills to work cross-functionally. You'll interview stakeholders, present business cases, and explain technical tradeoffs to non-technical leaders.

Preferred Requirements:

• You stay current with the latest releases and capabilities from Anthropic, OpenAI, Vercel, OpenClaw, and others in the agentic/applied AI space. You can talk about what shipped last month and what it changes.
• A portfolio of agent-powered workflows or internal tools you've built and deployed. Side projects, work projects, open source, anything with real users.
• You understand git, version control workflows, and basic security and safety practices when deploying AI into production environments.
• You've written about how you think about Applied AI (blog posts, threads, internal docs).
• You've worked with ops, finance, marketing, or another business function, not just engineering.
• You've taught non-technical people to use AI tools effectively.

Technologies You’ll Use

• Agent and Orchestration: Claude Code, Codex App Server, Sandboxes, MCP, n8n, Temporal, Agent SDK, custom TypeScript/Python pipelines
• Business Systems: Varies by team (Braze, Ramp, NetSuite, Jira, Linear, Slack, etc.)

5- year Sabbatical: After 5 years with CookUnity, you get a 4-week paid sabbatical

Paid family leave

Compassionate Leave: 3-5 days each time the need arises

A generous amount of CookUnity credits to enjoy our amazing meals, added to your account, monthly

Wellness perks: access to fitness subsidies to build a healthy lifestyle

AI-forward workplace: enterprise access to ChatGPT and Claude to help you work smarter and grow faster

Awesome opportunity to join a company that is looking to change how we eat and how chefs work!

Learn More About CookUnity

We believe great leadership starts with alignment on vision, values, and ways of working. To give you deeper insight into who we are and what we're looking for, we invite you to explore: CookUnity's Leadership Principles . The values and behaviors that guide how we operate, collaborate, and scale.

We hope this provides valuable insight into our culture and how we work. If this excites you, we'd love to connect!

Compensation

All final pay rates will be determined by candidates experience, knowledge, skills, and abilities of the applicant, internal equity, and alignment with market data.

Pay Range for this position

$130,000 — $190,000 USD

If you’re interested in this role, please submit your application, and if we think you might be a fit, we'll get in touch with you.Thank you for your time!

CookUnity is an Equal Opportunity Employer. We are dedicated to creating a community of inclusion and an environment free from discrimination or harassment. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, age, sexual orientation, gender identity, national origin, citizenship status, protected veteran status, genetic information, or physical or mental disability.