Applied Research Scientist: model compression

At Orient Path, we partner with innovative deep-tech companies building the next generation of AI infrastructure.

About the Company

A deep-tech software startup of 6 people developing algorithms for LLM compression and optimization, founded in early 2025 by two former quantum physicists. The company raised a €3.5M Seed round in 2026, and plans to expand the team and compression offerings to Silicon Vendors, AI Enterprises, OEMs, and Cloud Providers.

We believe the next wave of AI adoption will be driven by compact, highly efficient models optimized for specific use cases, rather than large general-purpose cloud models.

About the Role

This is an applied research role. You'll develop new compression methods and ship them, not write papers about them. The cycle is short: read the literature, prototype, benchmark on real models, integrate into our pipeline, iterate with customers running compressed models in production.

You'll own significant technical scope from day one. Expect to work across the stack: pruning algorithms, quantization, evaluation infrastructure, and the production code that customers actually use.

Your impact

• Improve and extend the structural pruning algorithm to new architectures (MoE, multimodal, vision-language).
• Combine pruning with quantization (NVFP4/FP8/INT4, sub-4 bit mixed precision) in the compression pipeline.
• Expand and improve the model retraining pipeline (SFT, GKD, DPO, GRPO).
• Compress customer models (Llama, Qwen, Gemma, and proprietary fine-tunes) for cloud and edge deployment.
• Hardware-aware optimization for different accelerator targets (A100/H100/B300 and edge hardware).

What we're looking for

• PhD in computer science, machine learning, or equivalent.
• Published work on quantization, pruning, or LLM training.
• Production-grade Python code (not just Jupyter notebooks).
• Experience taking a method from paper to a working system on real models.
• Comfort working with LLMs, GPUs, and evaluating benchmarks.
• You ship. You finish things.

Nice to have

• Open-source contributions to ML infrastructure (vLLM, llama.cpp, transformers, TensorRT-LLM, bitsandbytes, GPTQ/AWQ implementations).
• Experience with MoE architectures or multimodal models (Qwen Omni).
• Background in kernel optimization.

Compensation & details

• Hybrid in Vienna.
• Visa sponsorship and relocation support available.
• Full-time
• Working language is English.