ML Engineer

About the role

ML Engineer | Nox Metals | Detroit, MI

American factories deserve a supply chain that moves as fast as they do. The next generation of American manufacturing is being built right now. Nox Metals is the supply chain behind it.

Nox Metals is a technology company in Detroit supplying aluminum plate, bar, and rounds to aerospace and defense manufacturers. We use software and automation to supply metal to American factories faster than the industry thought possible.

We need an ML Engineer to build the intelligence layer of the company. Cut-time models, nesting scoring, demand intelligence, sales order parsing, dimensional vision, cert OCR, and the next ten things we have not built yet. Every machine, every order, every shipment generates data, and you turn it into a moat. Nox Metals is an employer with real opportunity for long term career growth, this is a place to build a career, not just hold a job.

You will:

- Own ML end to end across applied production work, novel research, and production deployment

- Build cut-time models that predict how long every cut takes by alloy, thickness, geometry, and machine

- Build nesting scoring and optimization models that make WAYNE smarter every day

- Build demand intelligence and procurement models that tell us what to buy, when, and at what price

- Build NLP and LLM features for sales order parsing, RFQ ingestion, and customer communication

- Build vision and OCR systems for cert package automation and dimensional inspection

- Ship features end to end, model, API, UI, deploy, monitor, no handoffs, no waiting

- Own the full ML lifecycle, data collection, labeling, training, evaluation, deployment, monitoring, retraining

- Build the data infrastructure and feature pipelines that future ML work depends on

- Partner with the software team to embed ML into NOX NEST, WAYNE, and Gondor

- Walk the floor, talk to operators, schedulers, and buyers, your training data starts where the work happens

- Always ask questions, never guess when something is unclear

- Look at every system and figure out how to make it better

- Work safely every shift and hold your teammates to the same standard

You should be:

- 5+ years of ML engineering experience shipping production models to real users

- Deep technical foundation across applied ML, foundation models or novel architectures, and production deployment

- Strong in Python, modern ML frameworks (PyTorch, JAX, or comparable), and the surrounding tooling

- Comfortable shipping production code, you build the API, the integration, and the UI when that is what the job needs

- Fluent in MLOps, model monitoring, retraining, and the unglamorous work of keeping models alive in production

- Experienced collecting, labeling, and structuring training data from messy real-world systems