Research Engineer, AI Models
Core
Research and implement techniques to accelerate AI inference and build fine-tuning pipelines for modern AI models on custom silicon.
Role type
Research Engineer (AI Models)
Builds
Production-quality AI inference pipelines and benchmarking frameworks for the company's in-memory-computing architecture.
Domain
Artificial Intelligence / Hardware Systems
Deliverable
production ML models
Required skills
ML research, Python, PyTorch, quantization, sparsity, distillation, speculative decoding, caching strategies, hardware-aware optimization, profiling, LoRA, adapters
Preferred skills
Experience with large language models, diffusion-based generators, multimodal systems
Technologies
PyTorch, Python
Responsibilities
Research and implement state-of-the-art techniques to accelerate AI inference; Partner with hardware teams to ensure algorithmic improvements translate to real gains on silicon; Build profiling tools and comprehensive benchmarking frameworks; Build robust fine-tuning workflows for modern AI models
Seniority
Senior, hands-on IC
