Applied AI Inference Engineer: Benchmark & Optimize

CoreWeave; San Francisco (CA); On-site; USD 188,000 - 275,000; Full time

Benefits offered by this job

Medical insurance

Life Insurance

Disability insurance

Tuition Reimbursement

ESPP

Paid Parental Leave

Flexible PTO

Catered lunch

Job summary

CoreWeave is hiring an Applied AI Engineer to understand, measure, and improve the real-world performance of our inference platform. In the near term, you will build and run rigorous benchmarks, profile model and system behavior, identify bottlenecks, and drive targeted optimizations for both platform-wide and customer-specific workloads.

This role focuses on applied performance work within the Inference team, with opportunities to broaden as the product matures and the team expands.

Qualifications

• 4+ years of experience in machine learning, systems, performance engineering, or adjacent applied engineering work.
• Strong programming skills in Python and comfort in production engineering environments.
• Experience running empirical evaluations, benchmarks, or experiments and translating results into concrete engineering decisions.
• Familiarity with LLM inference systems and tools such as vLLM, SGLang, TensorRT-LLM, or similar model-serving stacks.

Responsibilities

• Build and maintain benchmarking workflows measuring latency, throughput, quality regressions, and cost across priority models and serving configurations.
• Benchmark the inference stack against realistic customer workloads to identify performance gaps and improvement opportunities.
• Profile model-serving behavior across frameworks, runtimes, and hardware configurations to find bottlenecks in prefill, decode, KV cache usage, batching, graph capture, quantization, and related systems.
• Drive targeted optimization efforts for specific customer and product workloads, including tuning serving configurations and validating changes against traces and benchmarks.
• Design and run experiments on model-serving techniques such as quantization, speculative decoding, caching strategies, routing, and other inference optimizations.

Skills

Python

Performance engineering

Empirical benchmarking

LLM inference systems

Technical communication

Tools

vLLM

SGLang

TensorRT-LLM

Nsight Systems

PyTorch profilers

Job description

CoreWeave is hiring an Applied AI Engineer to understand, measure, and improve the real-world performance of our inference platform. In the near term, you will build and run rigorous benchmarks, profile model and system behavior, identify bottlenecks, and drive targeted optimizations for both platform-wide and customer-specific workloads.

This role focuses on applied performance work within the Inference team, with opportunities to broaden as the product matures and the team expands.