Founding ML Engineer — Lead High-Performance AI Infra

Strativ Group; Palo Alto (CA); On-site; USD 420,000 - 500,000; Full time

Benefits offered by this job

In-office Palo Alto

Equity: 1-2% founding equity

Significant ownership from day one

Job summary

Strativ Group in Palo Alto is building AI infrastructure for the next generation of agentic AI. You will design and optimize production infrastructure for large-scale AI workloads, focusing on TPU and GPU inference, distributed serving, and runtime performance.

As part of a small founding team, you will work directly with the founders, own significant parts of the infrastructure, and help shape the architecture and direction toward autonomous, self-improving models with minimal human supervision.

Qualifications

• Strong background in ML systems or AI infrastructure.
• Experience with model inference and serving.
• Experience with distributed training or inference.
• GPU and TPU systems experience.
• High-performance or low-latency distributed systems.

Responsibilities

• Build and optimize production infrastructure for large-scale AI workloads.
• Focus on TPU/GPU inference, distributed model serving and scheduling.
• Optimize runtime, latency, throughput, and infrastructure cost.
• Ensure reliability, observability and smooth deployment.
• Create infrastructure for autonomous and agentic workloads.

Skills

ML systems

Model inference

Distributed training

GPU/TPU systems

Low-latency distributed systems

Scheduling & runtimes

Job description

Strativ Group in Palo Alto is building AI infrastructure for the next generation of agentic AI. You will design and optimize production infrastructure for large-scale AI workloads, focusing on TPU and GPU inference, distributed serving, and runtime performance.

As part of a small founding team, you will work directly with the founders, own significant parts of the infrastructure, and help shape the architecture and direction toward autonomous, self-improving models with minimal human supervision.