Runtime Engineer (C/C++) – AI Hardware

About the role

We are a fast‑growing tech company building custom server hardware for AI and machine learning. We are looking for a Runtime Engineer to design and maintain the core runtime that connects our compiler stack to the hardware, ensuring high performance and reliability.

Key responsibilities

• Design and own the core runtime architecture bridging compiler and hardware.
• Implement and optimise the execution engine, device memory management, and command‑submission layer.
• Collaborate with firmware, driver, hardware, and ML framework teams on concurrency, scheduling, and observability tooling.
• Make technical decisions that guarantee long‑term scalability, maintainability and extensibility.
• Profile, debug and optimise latency and throughput for AI workloads.

Required profile

• 5–8+ years of experience in systems software, runtime systems or performance‑critical infrastructure.
• Strong proficiency in C/C++ and Python.
• Deep understanding of operating‑system fundamentals, multi‑threading, synchronization, memory management and cache behaviour.
• Hands‑on experience close to hardware (GPU, accelerator, driver or firmware environments).

Required skills

• C/C++
• Python
• Operating‑system concepts, multi‑threading, synchronization
• Memory management, cache optimisation
• GPU/accelerator programming, command queues, DMA
• Profiling and performance optimisation
• Familiarity with MLIR, LLVM, CUDA, ROCm, TensorRT, TVM, XLA, ONNX Runtime
• Integration of custom back‑ends into PyTorch, ONNX or OpenXLA

What we offer

• Opportunity to shape the runtime stack of next‑generation AI hardware.
• Collaborative environment with compiler, firmware and hardware experts.
• Impactful work on real‑world AI workloads.