Staff Engineer, Distributed AI Inference Systems (Equity)

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

Benefits offered by this job

Equity

Job summary

Acceler8 Talent in San Francisco, CA, is seeking a Member of Technical Staff for distributed systems to design, build, and operate the platform that schedules AI workloads across thousands of nodes. This onsite role emphasizes ownership of architecture, reliability, and performance in a fast-growing environment.

You will collaborate with founders and engineers from Nvidia, Google AI, Intel, and Pixie Labs while shaping the platform’s technical foundation and engineering culture in a ~25-person

Qualifications

• Strong software engineering and CS fundamentals.
• Experience building or operating distributed systems in production.
• Proficiency in Go, C++, Python for systems programming.

Responsibilities

• Build orchestration, scheduling, and control-plane systems for large-scale AI inference workloads.
• Design reliable distributed systems across thousands of heterogeneous compute nodes.
• Improve fault tolerance, availability, observability, and operational resilience.
• Develop high-performance APIs for customers running mission-critical workloads.
• Diagnose performance bottlenecks and quantify impact of improvements.
• Make pragmatic architectural decisions in a fast-moving, early-stage environment.

Skills

Strong software engineering

Experience distributed systems

Concurrency and failure recovery

Quantify performance impact

Ownership in early-stage company

Go, C++, Python

Tools

Kubernetes internals

Distributed schedulers

RPC frameworks

Messaging systems

Queues and async processing

High-throughput APIs

Job description

Acceler8 Talent in San Francisco, CA, is seeking a Member of Technical Staff for distributed systems to design, build, and operate the platform that schedules AI workloads across thousands of nodes. This onsite role emphasizes ownership of architecture, reliability, and performance in a fast-growing environment.

You will collaborate with founders and engineers from Nvidia, Google AI, Intel, and Pixie Labs while shaping the platform’s technical foundation and engineering culture in a ~25-person