🛠 Tech Stack

💼 About This Role

You'll design and implement knowledge distillation pipelines to build smaller, faster models. Your work will directly impact model quality and cost efficiency. You'll collaborate with research to translate cutting-edge techniques into production-ready systems.

🎯 What You'll Do

• Design and implement knowledge distillation pipelines (teacher–student, etc.)
• Distill large foundation models into smaller, faster inference models
• Run and analyze large-scale training experiments
• Optimize training and inference performance (memory, throughput, latency)

📋 Requirements

• Strong background in machine learning or deep learning
• Hands-on experience with model distillation (LLMs or neural networks)
• Proficiency in PyTorch or JAX
• Experience with multi-GPU or distributed training setups

✨ Nice to Have

• Experience distilling LLMs or large sequence models
• Experience with inference optimization (quantization, pruning)
• Open-source contributions or research publications

🎁 Benefits & Perks

• 🔬 High ownership and direct impact on product
• 👥 Small, senior team with strong culture
• 💰 Competitive compensation + meaningful equity
• 🌍 Remote-friendly, async-first environment