**About Sitemark**
Sitemark builds the platform that turns drone imagery of solar power plants into actionable insights for asset owners, O&M teams, and EPCs. We process huge volumes of aerial RGB and thermal imagery, detect what matters (anomalies, defects, construction progress), and deliver it in a product our customers actually use day-to-day.
We need someone who can help scale our AI capability so it reliably ships and moves real business metrics.
## Tasks
**The role**
You'll own the AI/ML side of our platform: training and improving the computer-vision models that power our products, and making sure they actually ship and perform in production. Your work will raise our throughput across model implementation, training runs, and dataset iteration — directly unblocking the team and our customers.
We're looking for a **pragmatic** engineer-scientist who delivers computer-vision solutions and knows how to navigate the landscape. Models exist to solve real problems — if an off-the-shelf model fine-tuned on our data does the job, that's a great answer. We care about results in the product, not novelty in a paper.
No solar or energy background required — we'll teach you the domain; curiosity matters more.
## Requirements
**What you'll do**
* **Level up the MLOps backbone** that lets us ship models reliably: experiment tracking, reproducible training, dataset versioning, model registry, deployment pipelines, monitoring in production, and a feedback loop from labeled operations data back into training. This is where AI work meets engineering, and it's a big part of what makes this role impactful.
* **Train, fine-tune, and ship computer-vision models** for tasks like thermal anomaly detection and classification, defect detection on high-resolution imagery, object detection on drone imagery, and stitching/co-registration support.
* **Run the full experimental loop**: curate and improve datasets, design training runs, analyse errors, iterate.
* **Tackle harder architectural problems** when they matter — for example, models that need to reason over large spatial context (entire sites, not just tiles) where a standard fixed-resolution detector falls short.
* **Integrate models into the product** end-to-end. Your model isn't done when the metric looks good — it's done when it's running on real data in the platform and making the team or the customer faster.
* **Reason about business impact.** Pick problems and approaches based on what actually moves the needle for our products and operations.
## Benefits
**Who we're looking for**
**Must-have**
* **Strong applied computer vision / deep learning** experience. You've trained, fine-tuned, and debugged CV models — not just consumed APIs. You understand what's happening inside the models you use.
* **Hands-on with the experimental loop**: dataset curation, augmentation, training, error analysis, iteration. You're comfortable when results are bad and know how to diagnose why.
* **Pragmatic, product-oriented mindset.** You can reason about how a model will be used in practice and what "good enough" looks like for the business. You prefer the shortest path to a real result.
* **Strong fundamentals and clean engineering instincts.** You write code meant to live in production — readable, testable, maintainable — not just notebook scratch.
* **Open to learning the integration side.** You don't need to be a senior full-stack engineer on day one, but you should be motivated to grow into MLOps and integration work, and comfortable touching code beyond the model itself.
* **High intelligence and learning velocity.** We care more about how you think and how fast you grow than about years on a CV.
* Comfortable working in English in a small, fast-moving team.
**Big plus**
* Experience with **aerial / drone / remote-sensing imagery** (orthomosaics, geo-referencing, multi-band, large images).
* **Non-visual imagery** (thermal, multispectral) experience.
* Detection, segmentation, keypoint, or multi-scale architectures applied to large or high-resolution images.
* **MLOps experience** in production: experiment tracking, reproducible training, model registries, monitoring.
* **Full-stack experience** (Python, TypeScript, React, Postgres) — you'll get plenty of opportunities to use it.
* Weakly- or self-supervised learning, active learning loops.
How you'll work
* You report to the **Head of Product & Engineering**. Coaching and technical sparring with the **Engineering Lead**.
* You'll work in cross-functional squads with platform engineers and our product team.
* You'll partner closely with the operational teams and our customers. Tight feedback loop.
* We value shipping over perfection, _and_ getting the architecture right when it matters.
**Why this role is interesting**
* **Real impact, fast.** We have a clearly identified gap, a concrete roadmap, and customers waiting on the results. Your models will ship.
* **Breadth.** From dataset and model work, through MLOps, into product integration. You'll grow across the stack as much as you want to.
* **Strategic seat.** AI is central to where Sitemark is going. You'll help shape that direction, not just execute on it.
* **Pragmatic culture.** We care about results, not theatre. We pick the boring solution when it works and invest in the hard one when it doesn't.
**Location**
**Remote-friendly, within compatible time zones.** We have team members across Belgium and Poland and are open to additional locations with sufficient overlap with Central European working hours.