ML Research Engineer: Model Compression & Accessible AI

ML Research Engineer

Make AI Accessible & Sustainable

As an ML Research Engineer at Pruna AI, you will be instrumental in integrating and optimizing cutting‑edge machine learning compression methods. You will work on solutions that make AI models more accessible and sustainable while minimizing their carbon footprint.

Responsibilities

• Understand and implement compression methods from open‑source projects and research papers.
• Integrate these methods into our compression tool, ensuring they are user‑friendly and effective.
• Adapt and extend successful methods to support various architectures and use‑cases.
• Provide customer support, especially in early stages, and resolve issues promptly.
• Conduct thorough testing to ensure reliability and robustness of the compression tool.

Required Skills & Experience

• A M.Sc./Ph.D. in computer science or equivalent experience in software engineering with a focus on machine learning.
• Strong foundational knowledge of machine learning algorithms and statistical methods.
• Expertise in the PyTorch deep learning framework.
• Proficiency in the Python programming language.
• Ability to read, understand, and critique research publications.
• Experience in formalizing and conceptualizing new research ideas.
• Strong communication skills to convey complex research ideas.
• Creative, collaborative, and innovation‑focused attitude.
• Strong sense of project ownership and personal responsibility.
• Passion for making AI accessible to everyone.

Preferred Additional Experience

• Experience with compression methods such as quantization, pruning, and compilation.
• Ability to interpret and implement research ideas and algorithms.
• Additional programming skills (e.g., Triton, C++).

Pay & Benefits

We pay top market rates based on seniority and location, using publicly available data that we share with you during the process. Competitive benefit packages are also in development.