Nik Bamert
Systems & ML engineer based in Zurich, Switzerland.
I build performance-critical systems across machine learning, perception, and retrieval.
My background spans embedded systems, computer vision, quantization, and production ML infrastructure at scale.
I care about the boundary where algorithms meet systems constraints; latency, memory, reliability and performance in real-world systems.
You can also find me on LinkedIn or GitHub.
Recent articles:
Selected Experience
Independent — ML Systems Engineer · 2025–present
Building performance-critical ML systems with a focus on retrieval and matching, efficient representations, hardware-aware optimization, and agentic optimization workflows for real-time workloads.
Pallon (ETH spin-off) — Production ML & CV Systems · 2020–2025
Owned, operated, and scaled production 3D reconstruction and ML systems to millions of images per day, with a focus on robustness, high-performance C++ data pipelines, and shipping reliable tools and workflows for internal teams and end users.
ETH Zurich, CVG — Research Engineer · 2019–2020
Worked on neural network compression, quantization, and efficient representations with custom CUDA/C++ kernels.
ETH Zurich — BSc & MSc, Computational Science and Engineering · 2014–2019
Thesis work focused on efficient representations for machine learning and vision systems, including quantization-aware training, binary neural networks, and fast retrieval and matching of binary features.
Independent Consulting — Embedded Software Engineer · 2007–2014
Built bare-metal firmware, bootloaders, and custom drivers for real-time industrial infrastructure systems under tight memory and compute constraints.