Principal AI Engineer

Key Responsibilities

• Build the agentic layer: one coherent layer that every AI capability in the product runs on. Once it exists, adding AI to any stage of the manufacturing flow is a few weeks of feature work. The runtime and the tools Architect the agent runtime: a server-side loop with durable runs, retries, scheduled and event-driven triggers, and human-in-the-loop steps Build the tool layer that turns our catalog of transaction-safe business operations into typed, tenant- scoped, permissioned AI tools, for our own agents and for the outside world through MCP Evaluation and audit Make evals part of how we ship: fixture-based tests of every AI behaviour, wired into CI from day one Close the correction loop: every override, rejection and edit captured as structured signal, so evals and retrieval improve from real use Build agent auditing into the platform's tamper-evident action log as it lands: every agent step logged, attributable and replayable. Our customers pass AS9100 audits, and explainable AI is a feature we sell Grounding and operations Drive the event catalog: which business facts the product announces, from the office to the shop floor (SalesOrderCreated, GoodsReceived, JobRunningLate). Every agent run starts from one Grow the semantic grounding: a machine-readable model of the business and how it fits together, so agents retrieve facts instead of inventing them Own the agent authority model: what an agent may do, its budget, how much autonomy each workflow gets. Instrument the runtime so every step is metered and traced Run what you ship: your agents in production are yours, including the incident when one misbehaves
• What Success Looks Like First three months: one real workflow runs end to end on the agent runtime in production, with its evals in CI and every step in the audit log. First six months: more agents are live on the same layer, and at least one of them was built by one of the full stack engineers. First twelve months: adding AI to a stage of the flow is a few weeks of feature work for any engineer here, and you can show an auditor how any of it reached the answer it did.
• How We Work Linear as the single board: work traced from issue to acceptance criteria to PR, reporting as a by- product of the work A small team: full stack engineers with a lead, plus AI and platform specialists, on a .NET and Next.js platform on Azure Prototype-led: we design the flow before we build it, against a shared design system AI in daily use across the team: coding agents in the repo with the context they need, and AI tooling for research, prototyping and analysis A customer base we can pick up the phone to, and an implementation team on their sites every week
• Tech Stack You'll Use Backend: C#, .NET 10, Rebus messaging, SQL Server (database per company) Frontend: Next.js, React, TypeScript Cloud: Azure (Container Apps, Azure SQL, Service Bus, Front Door), Bicep, GitHub Actions AI: Model-agnostic by design, with MCP as the tool protocol Tooling: Claude Code, Linear, GitHub
• What We're Looking For You've taken multiple LLM-powered systems from prototype to production, at least one of them agentic (multi-step, tool-using, running unattended), and you can walk us through what broke and what you'd redo Product instincts and a builder's disposition: you can sit with a planner or a quoting manager, translate their workflow into an agent architecture without being handed a spec, then write the code, ship it, and talk to the people who use it Strong backend and systems engineering experience (5+ years). You've built event-driven systems, you can explain why the transactional outbox exists, and you think in contracts, idempotency and failure modes You treat evals and observability as part of the definition of done, and you've wired LLM evaluation and observability tooling You treat AI security as an engineering problem: injection containment, retrieved content handled strictly as data, and hostile inputs in the eval suite Clear opinions on build versus buy: you know which parts of an agent stack to take from providers and which parts you have to own Comfortable being first: setting standards, writing them down, and reviewing others' work against them Strong written communication: you'll work with a team split across time zones Preferred Experience You've shipped something in manufacturing, ERP, supply chain or industrial operations, or you're genuinely curious about how factories run Document extraction pipelines: structured extraction from PDFs and email, OCR cascades, confidence-scored human review

Recruitment Notice

Protect yourself by following these steps