AI Inference Orchestration - Distributed Systems Engineer

Acceler8 Talent; San Francisco, Northern (CA, KY); Hybrid; USD 150,000 - 350,000; Full time

Job summary

Acceler8 Talent seeks a Member of Technical Staff – Distributed Systems in San Francisco, CA, onsite. The role focuses on building the orchestration layer for heterogeneous AI compute, enabling scheduling and routing of inference workloads across GPUs, CPUs and accelerators.

Join a fast-growing AI infra team shaping the platform that powers modern workloads. Ideal candidates have production-grade distributed systems experience, strong Go/C++/Python skills, and familiarity with Kubernetes, RPC

Qualifications

• Strong experience building distributed systems in production.
• Experience with scheduling, orchestration, fault tolerance and concurrency.
• Knowledge of Kubernetes, RPC frameworks, asynchronous messaging or control-plane infrastructure.
• Strong programming experience in Go, C++ or Python.
• Experience with AI infrastructure or heterogeneous compute is a plus.

Responsibilities

• Build scheduling, orchestration and control-plane systems for AI compute workloads at scale.

Skills

Distributed Systems

Scheduling

Orchestration

Fault Tolerance

Concurrency

Kubernetes

RPC Frameworks

Async Messaging

Control-Plane

Go

C++

Python

AI Infrastructure

Job description

Acceler8 Talent seeks a Member of Technical Staff – Distributed Systems in San Francisco, CA, onsite. The role focuses on building the orchestration layer for heterogeneous AI compute, enabling scheduling and routing of inference workloads across GPUs, CPUs and accelerators.

Join a fast-growing AI infra team shaping the platform that powers modern workloads. Ideal candidates have production-grade distributed systems experience, strong Go/C++/Python skills, and familiarity with Kubernetes, RPC