Description
ElastixAI, Inc. is hiring a Software Engineer for its AI Inference Platform in Seattle, Washington, in a hybrid role requiring three days per week in the office. The position is a deeply technical compiler and performance engineering role focused on decomposing LLM workloads into efficient primitives, building IR transformations and code generation for novel hardware, co-designing optimizations with ML and hardware teams, and developing performance models, profiling tools, and benchmarking frameworks. The role requires a strong CS or related degree, systems-level experience with compilers or ML frameworks, proficiency in Python/C++, and familiarity with LLMs, compiler infrastructures, hardware compute models, quantization, and ML frameworks. The company offers competitive compensation, equity, and comprehensive benefits including medical, dental, and vision coverage.
