Student Researcher - (Seed Model - Infra - Compiler) - 2026 Start

What you'll do

• Develop MLIR-based compiler passes and optimize AI workloads for performance, memory efficiency, and scalability.
• Support model deployment pipelines and distributed training and inference acceleration.
• Benchmark and analyze model performance across hardware backends, collaborating with researchers and engineers on improvements.

What they ask for

• Currently pursuing a Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or a related technical field.
• Experience using or developing open source LLM inference frameworks such as vLLM or SGLang, and proficiency in at least one deep learning framework with model inference experience.
• Understanding of modern computing systems and familiarity with compilers, model optimization pipelines, or model execution workflows.
• Able to commit to working for 12 weeks in 2026.

Nice to have

• Experience with distributed or large-scale ML systems and related optimizations.
• Experience with GPU/TPU/NPU programming or high-performance computing and communication; understanding of AI compiler and model optimization stacks.

Tools

MLIR, vLLM, SGLang, PyTorch, Megatron, DeepSpeed, JAX, PyTorch Dynamo

AI focus

AI compiler optimization, model training and inference acceleration, and model deployment across GPU and NPU hardware.