Sr. Machine Learning - Compiler Engineer III, AWS Neuron, Annapurna Labs

Job Summary We are looking for a senior software engineer in the Compiler team for AWS Neuron, an SDK that optimizes complex ML models for AWS Inferentia and Trainium chips. The role involves building the next‑generation Neuron compiler, solving hard optimization problems, and collaborating with hardware, runtime, and machine‑learning teams. Key Responsibilities Design, implement, test, deploy and maintain compiler solutions that improve Neuron performance, stability and user interface. Build and optimize passes for transforming models from frameworks such as PyTorch, TensorFlow, JAX and others into efficient code for Inferentia and Trainium. Solve complex optimization problems for diverse ML workloads, including large language models (Llama, Deepseek), vision transformers, stable diffusion and multi‑model deployments. Collaborate with chip architects, runtime/OS engineers, scientists and apps teams to integrate hardware capabilities. Engage with open‑source communities (StableHLO, OpenXLA, MLIR) to influence and contribute to compiler development. Participate in design discussions, code reviews and communicate with internal and external stakeholders, including responding to open‑source queries. Implement tools to analyse numerical errors, verify passes and resolve compiler defects. A Day in the Life As you design and code solutions to help our team drive efficiencies in compiler architecture, you’ll create optimisation and verification passes, surface features for developers, and work in a startup‑like environment focused on the most impactful projects. Basic Qualifications Bachelor’s degree in computer science or equivalent. 5+ years of full software development life cycle experience. 3+ years of experience developing compiler features and optimisations. Proficiency in at least one of the following: C++ (preferred) or Python. Preferred Qualifications Master’s or Ph.D. in computer science or equivalent. Deep knowledge of compiler design, resource management, instruction scheduling, memory allocation, data transfer optimisation, compute‑graph optimisation, code generation and ISA. Experience with LLVM, MLIR or related technologies. Experience in large‑language‑model, vision or other deep‑learning areas. Equal‑Opportunity Statement Amazon is an equal‑opportunity employer and does not discriminate on the basis of protected veteran status, disability or other legally protected status. Location and Compensation Location: Cupertino, California, USA. Annual salary range: USD 193,300 – 261,500. Benefits include health insurance, 401(k) matching, paid time off, parental leave and more. Application Information Job ID: A10432392 #J-18808-Ljbffr