Full Stack Machine Learning Engineer

The role

The ML Engineer will take models from reference implementation to efficient execution on AI accelerator hardware. This involves model bring-up, developing MLIR-based lowering paths, and optimizing performance across the model, compiler, kernels, and runtime.

What you will do

• Bring up new models by understanding architectures, loading weights, and implementing execution paths
• Lower models to hardware using MLIR by developing dialects, transformations, and mappings
• Support model operations through compiler and kernel changes
• Optimize execution including operator fusion, tensor layouts, and parallel execution
• Optimize inference by tuning prefill, decode performance, KV cache, and quantization
• Validate model quality by investigating numerical differences and accuracy impact
• Diagnose bottlenecks using profiling, execution traces, and hardware counters
• Work with hardware, compiler, kernel, and runtime teams to deliver model support and benchmarks

Required qualifications

• Strong programming skills in C++ and Python
• Hands-on experience bringing up and debugging ML models in PyTorch or a comparable framework
• Practical experience with MLIR, including dialects, rewrite patterns, transformation passes, and lowering pipelines
• Understanding of compiler fundamentals, including intermediate representations, dataflow analysis, and code generation
• Understanding of transformer architectures, attention mechanisms, tensor operations, and numerical precision
• Experience profiling and optimizing workloads on GPUs or other AI accelerators
• Ability to debug correctness and performance issues across model code, compiler-generated code, kernels, and runtime execution

Nice to have

• Experience with LLM inference, including GQA, sliding-window attention, MoE, KV caching, and speculative decoding
• Experience with FP16, BF16, FP8, or low-bit quantization and their accuracy and performance tradeoffs
• Experience developing accelerator kernels or hardware-specific compiler backends
• Familiarity with distributed execution, model parallelism, and accelerator memory hierarchies
• Contributions to MLIR, LLVM, inference frameworks, or related open-source projects

About the company

Cerebras Systems builds the world's largest AI chip. The company works with leading model labs, global enterprises, and cutting-edge AI-native startups.