dEggs Unlimited is one of the world's largest suppliers of eggs, servicing the biggest retail and food manufacturing companies around the globe. Every day, we find homes for millions of eggs by tapping into our vast supply chain and customer networks. Bringing sellers and buyers together in fair market negotiations, we open up a world of possibilities for expanding their knowledge, reach, and access. With dedicated service teams and a mission to uphold transparency and trustworthiness, we create quick and creative solutions to help manage the ever-evolving demands of the global egg industry. 

The Role 

We leverage AI to bring food to every table. 

You are a hands-on quality engineer embedded with operations. You decide what "working" has to mean before anything gets built, you ship the fixes and improvements yourself rather than filing them, and you are the person who says whether it is fit to carry real money. AI-assisted development is how the work gets done. Human judgment, controls, and production quality are not negotiable. 

The Problem We Are Solving 

We are building the intelligent operating platform behind a global food supply chain, combining leading models, our own operational data and business rules, and the judgment of the people who trade for a living. 

Extracting an order from an email is no longer the hard part. The loop is. Forecast where the market is going, project demand forward by customer and by product, and know what we are long and short on any given day. Then decide what to buy and what to sell, build the load, and book the freight against a computed view of what that lane is actually worth. Trading, supply, freight, and the ledger stop being separate systems stitched together by a spreadsheet and become one connected flow, with a named person accountable at every point where money moves. 

The product layer is largely greenfield. You will be building it, not maintaining someone else's version of it, though it has to work with the operational systems the business already runs on. We move quickly and we build practical solutions that scale, not demos. 

A system that books freight and takes a position can be wrong in ways a test suite was never designed to catch: confidently, plausibly, expensively wrong. Somebody has to know how often, in which direction, and what it costs at the desk. That is you. 

The Orchestrator 

The person in this seat does not write a test plan and wait. They take a product surface, direct a fleet of agents at it, and produce working proof of what it does and where it breaks, at a volume of coverage that would not have been possible from one person two years ago. If your monthly token consumption would look alarming to a traditional engineering manager, you are probably working the way we work. What we measure is not the volume: it is whether you decompose work well, keep context under control, catch the plausible and wrong answer, and stand behind what ships. 

You do not need prior experience in our exact stack. What matters is whether you can build things, whether you take ownership, and whether you can hold the big picture while you do it. Think like a customer, act like an owner. 

This seat pairs that with a quality engineering background. You sit with the traders, the purchasing coordinators, and the logistics desks to learn what a wrong answer costs them, then own both halves: the product code and the proof. You deliver features, fixes, and improvements like anyone else on the team, and when you find a defect or an uncovered corner you ship the change yourself rather than filing it and waiting for another team. This is not a test management role. 

What You Will Own 

What Counts as Done: Before anything is built, agree with the desk and the engineer what "working" means in the operators' own terms, and what evidence settles it. Written down, in advance. Vague criteria are how a system ships and quietly fails. 

The Call to Go Live: You hold the gate: clear work quickly when the evidence is there, and say "not yet" when it is not, to people who want it live this week. The bar is the evidence, never the calendar. Where you and the platform engineering lead read that evidence differently, their bar wins; keep the argument about evidence rather than dates. 

A Fleet of Models Aimed at Our Own Product: Direct agents to generate suites, probe for the failure nobody specified, run evaluations over real operating history, and keep regression coverage alive as the platform moves under it. Separating the real findings from the merely plausible is your job. This is an operating capability, not a tool preference. 

Shipping the Fix, Not the Ticket: Your scope is the product a desk touches, not the tickets with your name on them. Integration seams, other people's features, a load's path across four services: if it is wrong where an operator meets it, you ship the fix yourself. The same goes for the improvement nobody asked for but the desk needs. 

Building It With the Business: You are in the build, not after it. Get real users onto real workflows early and validate with the people whose money is on it. Their "yes, this is right" beats a green pipeline. 

After Go-Live: Launch is where the interesting failures start. Own the triage, and the fix as often as not. Chase the quiet wrongness nobody files a ticket about. Operators should hear about a problem from you before they find it themselves. 

Honest Numbers on Nondeterministic Systems: Report how often the system is right, how often it is wrong and in which direction, and how often it hands back to a person, against a baseline you set first. Tell the desks when to trust it. 

Engineering Standards: Ship maintainable, tested, observable, secure systems, with explicit evaluations, audit trails, rollback paths, and safe failure modes. Agent-generated work is held to the same production standard as anything you type. 

What Success Looks Like 

In your first 90 days: 

• You have sat with at least two desks and can say what a wrong answer costs at each. 

• Acceptance criteria agreed in writing, in the operators' terms, on something already in flight. 

• An agent-built suite running in CI that has caught something real. 

In your first six months: 

• A release gate the team trusts: it has cleared work fast and blocked one thing that deserved it, and neither was controversial afterward. 

• An evaluation layer live over one production workflow, reporting those numbers to the desk. 

• A post-launch loop that runs, with triage owned, defects caught before the desk noticed them, and the fixes shipped by you. 

In your first year: 

• Release evidence live across more than one operational function, each with monitoring, rollback, an audit trail, and a stop path the desk controls. 

• A record of what the gate cleared, what it held, and what each call cost or saved, in the desks' own terms. 

The clearest sign that you are succeeding: a desk stops quietly double-checking the system by hand, because it has learned the system tells the truth about itself. 

What You Bring 

• Experience owning quality in production systems: acceptance criteria, evaluation strategy, and the judgment to know what evidence is enough and when holding a release is the wrong call. 

• You ship production code. You are accountable for what it does in production, however it was produced. Features, fixes, harnesses, and fixtures are all real software, and all of it is held to that standard. 

• Serious agentic development practice. Show us real parallel-agent work: how you decompose tasks, manage context, review and reconcile output, design tests and evaluations, an example of a failure you caught, and a case where you decided not to use an agent. Anonymize anything confidential. 

• Ownership. You have carried something end to end and been accountable for whether it worked, not for whether it shipped. That includes shipping fixes into code you did not write. 

• Enough backend, data, and deployment competence to build your own instrumentation, integrate systems, and debug production independently. 

• Judgment about correctness in nondeterministic systems: evaluations, observability, failure-mode thinking, guardrails, human escalation, and rollback. 

• You can explain a risk to people who are not engineers in terms of what it would cost them. 

• Experience working within messy operational reality, email, spreadsheets, chat threads, and phone calls, rather than assuming users take the tidy path. 

We do not screen on years of experience, and we do not screen on which technologies you have used. Seniority here is calibrated by scope, judgment, autonomy, and outcomes. Show us what you have built. 

Helpful Experience 

• Food distribution, logistics, retail and CPG, trading, ERP or EDI, financial operations, or other trading-partner ecosystems. 

• Ambiguous, high-ownership environments where building and proving were the same job: founder, early employee, software engineer in test who wrote production code, forward-deployed engineer. 

Team, Environment, and How Decisions Get Made 

You report to the Director of Technology and join a small, senior engineering team. This is a lead role in scope and judgment, not in headcount: it does not manage people. The platform engineering lead sets the engineering and evaluation bar, owns shared tooling and guardrails, and is the second reviewer on your work. Infrastructure, identity, and access control sit with the platform team. Priorities are agreed with the Director of Technology and the business leaders who own the affected desks. 

Our environment spans cloud services on Azure, relational and event-sourced data stores, services in Go and Python, a TypeScript front end, an enterprise ERP core, and a retrieval layer over the company's own operating history. You will not be expected to have used all of it. 

Note: Responsibilities may evolve as the business grows and priorities change. 

Why Eggs Unlimited 

• Join at the "second floor" of a hyper-growth company rapidly becoming a skyscraper – help build what comes next. 

• Outsized impact opportunity – building people, leadership, culture, & support continued expansion. 

• Access meaningful advancement opportunities as the company continues to expand. 

• Modern hardware and access to leading models and development tools, with clear security and data-handling guardrails rather than blanket tool bans. 

Compensation and Benefits 

• Base Salary: $180,000 - $210,000+ annually  

• Comprehensive medical, dental, and vision coverage. 

• Company-paid life and disability insurance. 

• 401(k) plan with company match. 

• Generous PTO accruals, increasing each year. 

• Free daily lunch, snacks, and refreshments.