ML Compiler Engineer, Annapurna Labs

Amazon
Cupertino, CA, USA2026-05-21ONSITE

About the job

The AWS Neuron Compiler team is actively seeking skilled compiler engineers to join our efforts in developing a state-of-the-art deep learning compiler stack. This stack is designed to optimize application models across diverse domains, including Large Language and Vision, originating from leading frameworks such as PyTorch, TensorFlow, and JAX. Your role will involve working closely with our custom-built Machine Learning accelerators, including Inferentia/Trainium, which represent the forefront of AWS innovation for advanced ML capabilities, powering solutions like Generative AI.

Responsibilities

Solve challenging technical problems, often ones not solved before, at every layer of the stack.

Design, implement, test, deploy and maintain innovative software solutions to transform service performance, durability, cost, and security.

Research implementations that deliver the best possible experiences for customers.

Qualifications

Minimum

Bachelor's degree in Computer Science, Engineering, Mathematics, or a related field

3+ years of non-internship professional software development experience

Proficiency with 1 or more programming languages (C++ preferred).

2+ years of experience in optimization algorithms, graph-theory, hardware bring-up, FPGA placement and routing algorithms, or hardware resource management

Preferred

3+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience

M.S. or Ph.D. in computer science or related field

Strong knowledge in one or more of the areas of: compiler design, instruction scheduling, memory allocation, data transfer optimization, graph partitioning, parallel programing, code generation, Instruction Set Architectures, new hardware bring-up, and hardware-software co-design

Experience with LLVM and/or MLIR

Experience with developing algorithms for simulation tools

Experience is TensorFlow, PyTorch, and/or JAX

Experience in LLM, Vision or other deep-learning models