MTS, Research Engineer

📋 Description

• Conduct open-ended research on model architectures and training objectives.
• Reproduce and extend state-of-the-art results from papers.
• Build and scale distributed training infrastructure for large GPU clusters.
• Bridge science and engineering by turning ideas into robust code.
• Collaborate cross-functionally with researchers to unblock experiments via tooling and optimization.

🎯 Requirements

• Strong programming skills in Python, C++, or Rust; write clean, maintainable code.
• Deep knowledge of ML frameworks: PyTorch, JAX, or TensorFlow.
• Experience with large distributed systems and parallel computing (CUDA, NCCL, MPI).
• Strong foundation in linear algebra, calculus, probability, and statistics.
• Proven track record implementing complex deep learning algorithms from scratch.
• Nice-to-have: Master’s or PhD in CS/ML or related field (or equivalent industry experience).

🎁 Benefits

• Solve hard problems at the AI infrastructure frontier.
• Build cutting-edge tech that impacts AI globally.
• Ownership and impact in a fast-growing startup.
• Equity in a fast-growing startup.
• Comprehensive benefits package.
• Fireworks AI is an equal-opportunity employer.