MLOps Engineer

Artificial Intelligence holds immense potential for improving our lives and our work. One key challenge is its effective application in manufacturing. At EthonAI, you will have the unique opportunity to shape the manufacturing landscape across entire industries. As a member of our team, you will have the chance to tackle exciting engineering challenges from distributed computing to computer vision, using state-of-the-art technologies.

Who is EthonAI?

EthonAI is a technology leader in Industrial AI trusted by global manufacturers to optimize cost, quality, and speed. Our Platform contains purpose-built applications with proprietary AI, integrated into a scalable infrastructure. Our modules automate insight generation, ensure stable processes through closed-loop control, and build resilience against skill gaps and labor shortages.

We are multinational, multifaceted, and action-oriented. We are intentional about the principles that guide us every day: create immediate impact and value, play in the top league, and create the best place to work and grow.

What is this job about?

We are looking for an MLOps Engineer to help us build our next-generation industrial AI  platform. This role is about turning cutting-edge research models into production-ready deployments: models are prepared and managed in the cloud, then exported and deployed for high-performance inference at the factory edge.

You will design how models are packaged, shipped, and served. You’ll build the infrastructure that ensures our models are portable across environments and efficient on constrained hardware. This is not a research role; it is about making AI run reliably at scale in real factories.

We expect you to be self-driven, eager to learn, and motivated to take ownership of key parts of our MLOps stack.

First and foremost, we believe in curious people who are eager to learn and grow. Please also reach out if you don’t check all the points mentioned here.

Your Roles & Responsibilities

• Design secure workflows for artifact management & distribution (model checkpoints, exports, registries).

• Build pipelines for model packaging & export (PyTorch/DeepSpeed → ONNX, TorchScript, or hybrid).

• Develop and maintain serving infrastructure (Triton, KServe, or BentoML) for both edge and cloud.

• Ensure cross-platform reproducibility across CPU/GPU environments, with CPU fallback when needed.

• Define and enforce versioned I/O schemas so models remain compatible as they evolve.

• Optimize inference performance on constrained hardware (model caching, batching, minimizing cold starts).

• Provide observability: latency, throughput, resource utilization, and model drift monitoring.

Your Experience & Skills

• Proven experience deploying ML models using at least one serving framework (Triton, KServe, or BentoML).

• Strong background in PyTorch (or JAX/TensorFlow); hands-on experience with ONNX export and debugging custom ops.

• Experience with artifact management (e.g. DVC, MLflow, or object stores like S3/GCS/Azure).

• Solid understanding of containerization and runtime isolation (Docker, Kubernetes), plus alternatives (lightweight runtimes, binaries).

• Experience with CI/CD for ML (GitHub Actions, Buildkite, or similar) and version management.

• Familiarity with GPU scheduling & multi-tenancy (MIG, K8s GPU operator, Ray, or similar).

• Familiarity with cross-platform inference (ONNXRuntime, TensorRT, CPU acceleration).

• Proficiency in Python; working knowledge of C++/CUDA for performance-critical ops is a plus.

• Strong debugging skills for performance bottlenecks in model serving pipelines.

Why is EthonAI right for you?

We foster a culture where team members can grow and learn from each other. We are dedicated to being the workplace where each of us thrives.

We also offer a good handful of specific benefits:

• Comprehensive compensation package with stock options to become a co-owner of EthonAI.

• On-site work is important, with significant scope for flexible schedules and partially remote work.

• A CHF 2’000 yearly bonus when you take two consecutive weeks of vacation.

• Flexible parental leave.

• Support for continued learning, such as online courses and conferences.

• See your work being deployed in cutting-edge factories around the globe.

• We just moved to a brand new office and we are ready to grow

At EthonAI, there always are plenty of opportunities to step up and take charge. Other keys to our job satisfaction are the palpable impact we have on the real world, and being part of a top-notch team that is focused on a successful outcome for all.

EthonAI is an Equal Opportunity Employer. We are committed to creating a work environment that is fair and inclusive, where all decisions related to recruitment, advancement, and retention are free of discrimination. We particularly encourage applications from individuals traditionally underrepresented in tech.