I’m working with a European deep-tech company building next-generation AI acceleration hardware and compiler technology.
They’re looking for an AI Compiler Engineer to work at the intersection of compilers, AI and hardware, helping optimise how modern ML workloads execute on highly parallel accelerator architectures.
You’ll Be Working Across
- LLVM / MLIR / IREE / XLA
- AI graph lowering, optimisation & code generation
- PyTorch, ONNX & TensorFlow workloads
- Low-level performance optimisation & vectorisation
- RISC-V / custom AI accelerator hardware
- LLM & GenAI inference optimisation
Location : Grenoble area, France – Hybrid
Permanent position
If you’re a compiler engineer who enjoys working close to the hardware and wants to help shape a compiler stack around genuinely novel compute architecture, drop Harry Hansford a message.