LLM Inference Runtime Architect for AI Accelerator

United States Digital Space LLC; United States; Remote; USD 180,000 - 250,000; Full time

Job summary

United States Digital Space LLC is hiring a production-grade LLM inference runtime engineer to join the Hardware AI team. You will design and optimize the end-to-end runtime that maps frontier models onto our AI accelerator, balancing latency, throughput, and hardware utilization.

Work spans model architecture, systems software, and silicon interfaces, with emphasis on reliability, observability, and scalable performance in production environments.

Qualifications

• Strong systems programming experience in C++, Rust, Python, or comparable performance-oriented environments.
• Built or optimized runtimes, distributed systems, compilers, kernels, model-serving infrastructure.
• Understand modern LLM inference including prefill and decode behavior, batching, KV-cache tradeoffs, and model parallelism.

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.
• Enable new model features, execution patterns, numerical formats, and hardware capabilities in a reliable production runtime.
• Create profiling, observability, benchmarking, and performance-modeling tools that make runtime behavior measurable and actionable.
• Debug complex correctness, performance, and reliability issues spanning model code, runtime software, communication layers, and hardware.
• Turn workload insights into clear requirements for future generations of silicon and system architecture.

Skills

C++

Rust

Python

Distributed systems

Model-serving

Job description

United States Digital Space LLC is hiring a production-grade LLM inference runtime engineer to join the Hardware AI team. You will design and optimize the end-to-end runtime that maps frontier models onto our AI accelerator, balancing latency, throughput, and hardware utilization.

Work spans model architecture, systems software, and silicon interfaces, with emphasis on reliability, observability, and scalable performance in production environments.