Member of Technical Staff | Inference Platform

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Member of Technical Staff | Inference Platform based in Brazil.

This role focuses on the infrastructure that powers reliable, scalable machine learning inference across cloud and customer environments.
You’ll own the systems that execute models for both large-scale batch workloads and real-time APIs.
Your work will directly influence availability, latency, throughput, GPU utilization, and the cost of every prediction.
You’ll build and evolve Kubernetes-based inference infrastructure while solving challenging problems in scheduling, scaling, recovery, security, and isolation.
The role combines hands-on systems engineering with a strong product mindset, treating compute efficiency and operational reliability as core product features.
You’ll work across model serving, batch execution, data processing, GPU optimization, and customer-hosted infrastructure.
It’s an opportunity to take broad ownership of production ML infrastructure where technical decisions have measurable customer and business impact.