机器学习工程师 — 知识蒸馏
Machine Learning Engineer — Distillation
职位描述
我们正在寻找一名机器学习工程师，专注于模型压缩，帮助我们构建更小、更快、更高效的模型，同时不牺牲质量。你将在研究与生产之间工作——将前沿技术转化为可扩展的系统。
这是一个需要亲自参与并拥有实际责任的职位：你将设计压缩流程，运行大规模实验，并部署用于生产的模型。
你将负责
· 设计和实现知识蒸馏流程（教师-学生、自蒸馏、多教师等）
· 将大型基础模型压缩为更小、更快、成本更低的推理模型
· 运行并分析大规模训练实验，评估质量、延迟和成本权衡
· 与研究团队合作，将新的蒸馏想法转化为生产就绪的代码
· 优化训练和推理性能（内存、吞吐量、延迟）
· 为内部工具、评估框架和实验跟踪做出贡献
· （可选）为开源模型、工具或研究做出贡献
我们希望你具备
· 机器学习或深度学习的扎实背景
· 模型压缩（LLM或其他神经网络）的实际经验
· 对训练动态、损失函数和优化有扎实的理解
· 使用 PyTorch（或 JAX）和现代 ML 工具的经验
· 能够在多 GPU 或分布式环境中运行实验
· 能够权衡模型质量与性能
· 实用主义思维：你关注的是交付成果，而不仅仅是论文
加分项
· 具有 LLM 或大型序列模型压缩经验
· 具有推理优化经验（量化、剪枝、内核等）
· 熟悉语言模型的评估
· 有开源贡献或研究发表经验
· 在早期或快速发展的初创公司有经验
加入我们
· 参与核心模型质量和成本效率工作——不是边缘项目
· 高度自主，对产品和路线图有直接影响
· 小型、资深团队，具有强大的研究与工程文化
· 竞争性薪酬 + 有意义的股权
· 远程友好、以异步优先的环境
最初发布于 Himalayas
查看英文原文
About the Role
We’re looking for a Machine Learning Engineer focused on model distillation to help us build smaller, faster, and more efficient models without sacrificing quality. You’ll work at the intersection of research and production—taking cutting-edge techniques and turning them into systems that scale.
This is a hands-on role with real ownership: you’ll design distillation pipelines, run large-scale experiments, and ship models used in production.
What You’ll Do
- Design and implement knowledge distillation pipelines (teacher–student, self-distillation, multi-teacher, etc.)
- Distill large foundation models into smaller, faster, and cheaper models for inference
- Run and analyze large-scale training experiments to evaluate quality, latency, and cost tradeoffs
- Collaborate with research to translate new distillation ideas into production-ready code
- Optimize training and inference performance (memory, throughput, latency)
- Contribute to internal tooling, evaluation frameworks, and experiment tracking
- (Optional) Contribute back to open-source models, tooling, or research
What We’re Looking For
- Strong background in machine learning or deep learning
- Hands-on experience with model distillation (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 vs. performance tradeoffs
- Pragmatic mindset: you care about shipping, not just papers
Nice to Have
- Experience distilling LLMs or large sequence models
- Experience with inference optimization (quantization, pruning, kernels, etc.)
- Familiarity with evaluation for language models
- Open-source contributions or research publications
- Experience in early-stage or fast-moving startups
Why Join
- Work on core model quality and cost efficiency—not side projects
- High ownership and direct impact on product and roadmap
- Small, senior team with strong research + engineering culture
- Competitive compensation + meaningful equity
- Remote-friendly, async-first environment
Originally posted on Himalayas