Senior ML Systems Engineer: High-Perf Inference & Infra

Strativ Group; Palo Alto (CA); On-site; USD 600,000 - 1,000,000; Full time

Job summary

Strativ Group in Palo Alto is building a seed-stage AI infrastructure company focused on high-performance inference on TPUs and GPUs, with a longer-term goal of an agent cloud where models and agents can improve themselves. Engineers will work directly with founders to shape architecture and direction from day one.

The role covers ML systems, distributed systems and AI infrastructure with potential work on low-level serving or infrastructure for autonomous, self-improving workloads.

Qualifications

• Strong background in at least one area: ML systems/AI infrastructure, model inference/serving, distributed training/inference, GPU/TPU systems, scheduling/runtimes or compiler-level optimization.

Responsibilities

• Build and optimize production infrastructure for large-scale AI workloads.
• Work on ML systems, distributed systems and AI infrastructure.
• Own significant pieces of the system from day one.
• Focus on low-level serving and runtime performance or infrastructure for autonomous agent workloads.
• Improve latency, throughput and infrastructure costs.
• Enhance reliability, observability and deployment of AI workloads.

Job description

Strativ Group in Palo Alto is building a seed-stage AI infrastructure company focused on high-performance inference on TPUs and GPUs, with a longer-term goal of an agent cloud where models and agents can improve themselves. Engineers will work directly with founders to shape architecture and direction from day one.

The role covers ML systems, distributed systems and AI infrastructure with potential work on low-level serving or infrastructure for autonomous, self-improving workloads.