Ai Distilation Expert

What You’ll Do: Design and run knowledge distillation pipelines– teacher/student setups for large neural models (LLMs and/or generative vision models) Optimize for latency– reduce inference cost via distillation, quantization, pruning, and mixed precision Evaluate rigorously– build empirical quality-vs-latency comparisons and A/B test variants Own training loops– write and debug full PyTorch training code, not just run existing scripts Ship to production– deploy distilled models on live GPU servers and measure real-world performance Must Have 2 years hands-on PyTorch, including training/fine-tuning models from scratch – not just serving pretrained ones Proven experience with model distillation– you’ve actually distilled a model and measured the results Strong grasp ofmodel compression techniques : quantization, pruning, knowledge distillation, LoRA/parameter-efficient methods Solid understanding ofloss designfor distillation (KL divergence, feature/logit matching, perceptual losses) Comfortable reading and extendingdense, lightly-documented research code Strong PlusExperience distillingautoregressive LLMs or speech models Experience withGANs, diffusion, or flow-matchingmodels GPU inference optimization: torch.compile, CUDA memory management, multi-GPU setups Familiarity with streaming/real-time ML systems Working StyleWe operate like a research lab: empirical, fast iteration, incomplete docs, self-directed testing. You’ll need to be comfortable designing your own experiments and pushing for more engineering structure as you go.