Senior Performance Modeling Engineer, AI Inference Deployments

Location: Remote (United States)

Base salary: $220,000–$270,000 per year

Company

hirify.global develops AI inference accelerators and systems for low-latency, high-throughput large language model inference. Its Atlas systems are in production on Oracle Cloud Infrastructure, while the Asimov ASIC and Titan system target frontier-scale inference deployments.

What you will do

• Partner with customers and product teams to turn deployment questions into quantified studies with assumptions, options, metrics, and recommendations.
• Compare equivalent inference deployments across Positron hardware, GPUs, and other accelerators, explaining the drivers of performance differences.
• Build a standalone performance-estimation tool that customers can run on their own workloads.
• Model large-scale inference topologies, including tensor, pipeline, expert, and data parallelism, batching, context length, and mixed Positron-plus-GPU configurations.
• Model network and system effects such as interconnect latency and bandwidth, redundancy, and throughput limits as chip count grows.
• Validate and calibrate analytical and simulation-based models against hardware measurements as chips, software, and workloads evolve.

Requirements

• 5+ years of experience in performance modeling, capacity planning, or systems architecture for large-scale AI inference, HPC, or data-center systems.
• Experience building analytical or queueing performance models and calibrating them against measured systems.
• Deep systems-level understanding of LLM inference, including prefill versus decode, KV cache, parallelism strategies, mixture-of-experts routing, batching, time-to-first-token, and tokens per second.
• Working knowledge of data-center networking, including latency, bandwidth, and topology, plus GPU performance characteristics.
• Ability to work from incomplete information, state assumptions explicitly, and provide answers with error bars.
• Strong Rust skills, or expert-level C/C++ skills with willingness to work in Rust day to day, plus Python proficiency for analysis, experiments, and visualization.
• Excellent communication skills for explaining sizing results, performance drivers, and confidence levels to engineers and customers.
• Candidates must currently be authorized to work in the United States.

Nice to have

• Experience sizing or benchmarking production inference deployments across many accelerators.
• Experience building customer-facing performance or total-cost-of-ownership tools.
• The organization is open to hiring at a more senior level for the right candidate.

Culture & Benefits

• Remote-first work with a company-provided computer and home office setup.
• Fully company-paid medical, dental, and vision insurance for employees and dependents.
• Company-paid life and disability coverage, with additional voluntary coverage options.
• Unlimited paid time off and 13 paid company holidays.
• Competitive salary, equity, and a 401(k) with company matching from day one.
• No new visa sponsorship is available; H-1B transfers may be facilitated for eligible candidates.