Based on decades of parallel computing research at MIT, Neural Magic has developed deep learning model sparsification tools and a CPU inference engine.

Our solution helps data scientists and ML engineers sparsify and quantize deep learning models to minimize footprint and run on CPUs at GPU speeds. Please look through our GitHub repos to get a feel of what we are about, and if still interested, apply to join our team.

We are looking for senior engineers excited to work with machine learning, parallel and concurrent algorithms, interested in working closely with the founding team and who want to contribute to solving challenging, high performance computing problems.

PRIMARY JOB REQUIREMENTS

• 5-7+ year of experience coding in modern C++ and writing C++ libraries, writing high performance code for compute intensive operations
• Low level systems developer (x86 assembly) and multicore programming
• Experience working with parallel and concurrent algorithms
• Familiarity with deep neural network models and techniques
• Likes dynamic work environment
• Likes to learn new technology concepts

COMMUNICATION & CULTURE

• Self-directed practitioner who learns fast and is comfortable operating a blank slate environment
• Strong communications skills with both technical and non-technical team members
• Strong sense of project ownership and personal responsibility