Founding Senior Performance Engineer - Remote + Equity

Mission.dev; Montreal; Hybrid; CAD 180,000 - 240,000; Full time

Job summary

Mission.dev is seeking a Senior Performance Engineer to join as a founding team member. You will architect solutions across the full inference stack, owning kernel optimization, serving engine design, and orchestration improvements.

The role offers remote work from Canada and a chance to influence cost and energy efficiency at scale. You will translate research into production systems, pushing GPU utilization toward maximum efficiency while shaping distributed inference across multi-GPU,

Qualifications

• Experience building large-scale production inference or training systems.
• Strong understanding of GPU architectures and kernel behavior.
• Proficient in distributed systems, scheduling, and fault tolerance.

Responsibilities

• Design and build high-performance inference systems for multi-GPU and multi-node deployments.
• Develop kernels and runtime paths to maximize GPU utilization and memory efficiency.
• Extend serving engines with advanced batching, KV-cache management, and scheduling policies.
• Architect distributed inference systems with autoscaling, load balancing, and latency SLOs.
• Profile and analyze the full inference lifecycle to resolve bottlenecks.
• Implement techniques such as speculative decoding, tensor parallelism, and mixture-of-experts serving.
• Collaborate with hardware partners to improve energy efficiency and reduce costs.
• Contribute to internal tooling and open-source projects in the inference ecosystem.

Skills

Large-scale inference systems

GPU architectures

Inference frameworks

Distributed systems

Performance debugging

End-to-end ownership

Tools

Kubernetes

Observability stacks

Job description

Mission.dev is seeking a Senior Performance Engineer to join as a founding team member. You will architect solutions across the full inference stack, owning kernel optimization, serving engine design, and orchestration improvements.

The role offers remote work from Canada and a chance to influence cost and energy efficiency at scale. You will translate research into production systems, pushing GPU utilization toward maximum efficiency while shaping distributed inference across multi-GPU,