Full Stack Machine Learning Engineer
Cerebras · Bengaluru, IND
CHECKED 8H AGO
Infrastructureremote
At a glance
Highlights
- Own model bring-up from reference implementation to efficient accelerator execution.
- Optimize prefill, decode, KV cache and batching for ultra high-speed inference.
- Work on the world's largest AI chip delivering 10x faster inference speeds.
Ideal candidate
A systems-minded ML engineer who loves taking models from prototype to fast, correct execution on novel hardware and collaborating across hardware and compiler teams.
Requirements
- Strong programming skills in C++ and Python
- Hands-on experience bringing up and debugging ML models in PyTorch or comparable framework
- Practical experience with MLIR including dialects, rewrite patterns, passes and lowering pipelines
- Understanding of compiler fundamentals including IRs, dataflow analysis and code generation
- Understanding of transformer architectures, attention, tensor ops and numerical precision
- Experience profiling and optimizing workloads on GPUs or other AI accelerators
- Ability to debug correctness and performance across model, compiler, kernels and runtime
Lab profile
About Cerebras
Builds wafer-scale AI chips and cloud systems for ultra-fast training and inference.
What they build
- Wafer-scale AI chips
- AI training systems
- Cloud inference service
Known for
- 56x larger chips than GPUs
- 10x faster inference than GPU clouds
- Industry-leading training speed