jobs
Full Stack Machine Learning Engineer
Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. This architecture allows Cerebras to deliver industry-leading training and inference speeds; over 10 times faster than…
En inglés
- Company
- Cerebras
- Location
- Bengaluru, IND
- Status
- Open
- Posted
- 2026-10-09 10:40 UTC
Cerebras is hiring a machine learning engineer in Bengaluru, hybrid, to take models from reference implementations to efficient execution on its AI accelerator hardware. The work covers model bring-up, MLIR-based lowering, kernel and runtime changes, operator support such as attention and matrix multiplication, inference tuning (prefill, decode, KV cache, batching, quantization), numerical validation, and profiling on accelerators. The posting asks for C++ and Python, PyTorch debugging, hands-on MLIR experience, compiler fundamentals, and transformer knowledge; accelerator kernel and LLM inference experience are preferred. It spans model, compiler, kernel and runtime work.
Original job posting