Model Runtime Engineer for Frontier AI on Custom Silicon

OpenAI; United States; Remote; USD 180,000 - 230,000; Full time

Job summary

OpenAI is seeking a skilled engineer to build the model runtime within the inference engine that executes frontier models on our custom silicon. You will bridge models on hardware with the cluster serving software, translating workloads into efficient execution while optimizing throughput, latency, and reliability.

You will collaborate across model architecture, distributed systems, compilers, kernels, and silicon to design a production-grade runtime, comparable to systems like vLLM but tailored

Responsibilities

• Design and implement the LLM inference runtime for frontier models running on custom silicon.
• Build scheduling, continuous batching, memory management, KV-cache management, and execution orchestration for high-performance inference.
• Develop distributed execution strategies across chips, hosts, and racks, including model partitioning, communication, and synchronization.
• Optimize end-to-end latency, throughput, memory efficiency, and hardware utilization across diverse model architectures and serving workloads.
• Partner with kernel, compiler, architecture, and silicon teams to co-design interfaces and remove performance bottlenecks across the stack.

Job description

OpenAI is seeking a skilled engineer to build the model runtime within the inference engine that executes frontier models on our custom silicon. You will bridge models on hardware with the cluster serving software, translating workloads into efficient execution while optimizing throughput, latency, and reliability.

You will collaborate across model architecture, distributed systems, compilers, kernels, and silicon to design a production-grade runtime, comparable to systems like vLLM but tailored