Edge ML Engineer: Distill & Detect for Embedded Systems

Blackshark; Zürich; On-site; CHF 120,000 - 180,000; Full time

Job summary

Harmattan AI in Switzerland is hiring an ML Research Engineer for the Detect&Track Distillation team. You will distill large foundation models into efficient, task-specific components for edge devices across Lausanne, Paris, or Zurich.

Work spans target detection, classification and re-identification, focusing on performance under hardware inference constraints. You will collaborate with cross-functional teams and mentor juniors as needed.

Qualifications

• Degree in a STEM field (e.g., Computer Science, Engineering, Mathematics).
• Proven experience with vision neural networks, target detection architectures, or re-identification tasks.
• Hands-on expertise in knowledge distillation, model compression, and deploying networks onto constrained embedded systems or edge hardware (Jetson, NPUs).
• Proficiency in MLOps, GPU compute, and building training pipelines and loggers.
• Highly structured, analytical, task-oriented and research-driven.
• Excellent communication and influence skills, with ability to present benchmarking data to stakeholders.
• Willingness to work in a fast-paced defense tech environment.

Responsibilities

• Distill large foundation models into highly specific, efficient components for edge devices.
• Optimize neural networks for constrained embedded systems using quantization, pruning, and LoRA.
• Build, modify and manage training, evaluation, and MLOps pipelines with reproducibility and version control.
• Collaborate on data curation and create task-specific datasets to improve model accuracy.
• Benchmark distilled models for performance and latency aligned with real-world deployments.
• Stay at the forefront of CV and quantization research to introduce new methods.
• Work closely with cross-functional teams to deliver robust solutions and possibly mentor juniors.

Skills

Deep Learning

Computer Vision

Model Compression

Edge AI

MLOps

GPU Compute

Infrastructure

Education

STEM degree

Tools

Jetson

NPUs

Job description

Harmattan AI in Switzerland is hiring an ML Research Engineer for the Detect&Track Distillation team. You will distill large foundation models into efficient, task-specific components for edge devices across Lausanne, Paris, or Zurich.

Work spans target detection, classification and re-identification, focusing on performance under hardware inference constraints. You will collaborate with cross-functional teams and mentor juniors as needed.