Machine Learning Engineer - New Grad
Core
Train and evaluate speculative decoding models, implement optimization techniques (quantization, sparsity, distillation), and build agentic systems to make large language models cheaper and more capable.
Role type
New Grad Machine Learning Engineer (LLM inference & optimization)
Builds
Speculative decoding models, optimized LLM serving stack, agentic workflows
Domain
AI Infrastructure / Large Language Models / Model Efficiency
Deliverable
production ML models
Required skills
Python, PyTorch/TensorFlow/JAX, Transformer architectures, LLM training/inference pipeline, experimental design, numerical computing
Preferred skills
M.S./Ph.D., speculative decoding, distillation, quantization, agentic systems, reinforcement learning, distributed training frameworks
Technologies
PyTorch, TensorFlow, JAX, FSDP, DeepSpeed, Megatron, vLLM, SGLang, TensorRT-LLM
Responsibilities
Train and tune speculative decoding models to increase acceptance rates; Develop optimization techniques for model quality and resource efficiency; Build and evaluate agentic systems for tool use and planning; Design rigorous evaluations and benchmarks; Translate research into working implementations; Partner with performance and compiler teams to ship improvements.
Seniority
Junior, New Grad
