Vienna / Remote

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

One of our clients is developing a fundamentally new approach to LLM model compression, enabling large language models to run significantly more efficiently without sacrificing quality.

As the company grows beyond its research phase, they're looking for a Software Engineer who will establish the engineering foundations around cutting-edge AI research.

You won't be inventing the compression algorithms. You'll be the engineer who turns world-class research into world-class software.

Working directly with the founders and research team, you'll transform research prototypes into scalable libraries, production-ready tooling, and an engineering platform that will support the company's future growth.

What You'll Own

You'll become the engineering bridge between cutting-edge research and production AI systems.

Your work will include:

• Designing and refactoring the company's core Python libraries around pruning, quantization, retraining and evaluation
• Building clean, reusable software packages instead of research prototypes
• Creating internal developer tooling, benchmarking infrastructure, CI pipelines and reproducible environments
• Integrating compression pipelines with modern inference frameworks including vLLM, TensorRT-LLM and llama.cpp
• Improving software architecture, maintainability and developer experience across the codebase
• Helping establish engineering standards as the company scales while working closely with researchers and founders

What We're Looking For

Software Engineer first

We're looking for someone who naturally thinks like a software engineer.