Senior Performance Engineer – GPU Inference & Efficiency

Mission.dev in Montreal is seeking a Senior Performance Engineer to own and optimize the entire inference stack for large-scale models. You will architect kernel-level optimizations, shape the serving engine, and improve orchestration to maximize throughput under power and latency constraints.

You will collaborate with hardware partners and contribute to tooling and open-source projects, translating research into production-ready systems that push GPU utilization toward its limits.