Machine Learning Engineer (Distillation)

TL;DR

Machine Learning Engineer (Distillation): Design and implement knowledge distillation pipelines to create smaller, faster models from large foundation models with an accent on quality preservation, latency reduction, and cost efficiency. Focus on running large-scale experiments, optimizing training and inference performance, and shipping production-ready systems.

Location: Remote (world)

Company

hirify.global develops efficient AI models through advanced distillation techniques at the intersection of research and production.

What you will do

• Design and implement knowledge distillation pipelines including teacher-student, self-distillation, and multi-teacher approaches
• Distill large foundation models into smaller, faster, cheaper versions for inference
• Run and analyze large-scale training experiments evaluating quality, latency, and cost tradeoffs
• Collaborate with research team to translate new distillation ideas into production code
• Optimize training and inference performance for memory, throughput, and latency
• Contribute to internal tooling, evaluation frameworks, and experiment tracking

Requirements

• Strong background in machine learning or deep learning
• Hands-on experience with model distillation on LLMs or other neural networks
• Solid understanding of training dynamics, loss functions, and optimization
• Experience with PyTorch (or JAX) and modern ML tooling
• Comfort running experiments on multi-GPU or distributed setups
• Ability to reason about model quality versus performance tradeoffs
• Pragmatic mindset focused on shipping production systems

Nice to have

• Experience distilling LLMs or large sequence models
• Experience with inference optimization including quantization, pruning, and custom kernels
• Familiarity with language model evaluation
• Open-source contributions or research publications
• Experience in early-stage or fast-moving startups

Culture & Benefits

• Work on core model quality and cost efficiency with high ownership and direct product impact
• Small, senior team emphasizing strong research and engineering culture
• Competitive compensation with meaningful equity
• Remote-friendly, async-first environment