Senior Staff Applied AI Inference Engineer

What you'll do

• Profile and optimize inference stacks, serving architectures, frameworks, and CUDA kernels for latency, throughput, and cost.
• Adapt and deploy optimizations for customer workloads, taking services from proof of concept to monitored production.
• Build and support inference software and product features, collaborating with customers and engineering and product teams.

What they ask for

• Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics, or a related field.
• Production coding experience in one or more general-purpose languages, such as Python or C++; Python strongly preferred.
• Familiarity with LLM inference optimization methods and serving frameworks such as vLLM or SGLang, including kernel-level profiling.
• GPU knowledge, hands-on interest and experience with large language models, and working knowledge of AI/ML pipelines and model deployment.

Nice to have

• Experience with CUDA or comparable technologies.
• Experience with Docker and Kubernetes.

Pay

up to $250,000 - $300,000 + Bonus (base salary; pay basis not specified)

Tools

Python, C++, vLLM, SGLang, CUDA, Docker, Kubernetes

AI focus

Applied LLM inference optimization and production deployment, including serving architecture design, profiling, and performance tuning.