About the job

Flux Computing is seeking a highly experienced Compiler Engineer (Contractor) for a 6-month engagement outside of IR-35 to join their permanent team in building the ML backend and functional simulator for next-generation optical tensor processing units (OTPUs). The successful candidate will deliver a production-ready ML backend—including compiler, runtime, debugger, and simulator—capable of running large AI models with accuracy and efficiency. Key responsibilities include implementing a runtime that integrates seamlessly with PyTorch, TensorFlow, and JAX (supporting asynchronous execution and multiple devices), developing an extensible compiler that supports optimization patterns like fusion, layout optimization, tiling, and scheduling, and creating debuggers with runtime assertions, compile-time dumps, tensorboard timelines, and JAX I/O callbacks. Additionally, the role involves building a functional simulator that mimics kernel-space drivers, enabling the software team to lower operations ahead of hardware readiness. Candidates should have 5+ years of experience in software engineering with strong expertise in C/C++, compiler internals, ML frameworks, and performance optimization, along with a bachelor’s degree in computer science, engineering, mathematics, or a related field. Strong problem-solving ability, creativity, and collaboration skills are essential, as well as proven experience in high-paced, dynamic environments. This is an exciting opportunity to contribute to innovative AI hardware and software while working remotely with a fast-growing team at the forefront of optical computing.