Machine Learning Engineer, AI Models
Core
Porting, tuning, and validating LLMs and vision models on custom AI hardware accelerators to optimize performance and accuracy.
Role type
Machine Learning Engineer (AI Models)
Builds
High-performance deployments of state-of-the-art LLMs and vision models on custom RISC-V AI accelerators
Domain
AI Hardware / Custom Silicon / Machine Learning
Deliverable
production ML models
Required skills
PyTorch, TensorFlow, modern ML model architectures (transformers), software engineering fundamentals, debugging, problem-solving
Preferred skills
profiling, performance tuning, quantization, flash attention, kernel fusion, memory hierarchies, C++, CUDA, systems programming
Technologies
PyTorch, TensorFlow, RISC-V, CUDA
Responsibilities
Bring up, run, and debug modern ML models; Analyze model behavior and identify bottlenecks; Improve efficiency and scalability of model execution; Collaborate with compiler and hardware teams; Translate research-grade architectures into production-grade deployments
Seniority
Open to all levels (assessed during interview)
