Cerebras

3 months ago

Senior Performance Engineer, Inference

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 3 hours agoStatus: Live

Job Summary

Build and maintain reproducible inference performance benchmarks for real customer workloads, measuring metrics such as tokens per second, time to first token, latency under concurrency, and total cost of ownership. Develop and update a competitive pricing intelligence model across inference providers to support enterprise contract recommendations. Stay current with GPU optimization research and third-party benchmarking sources, and produce actionable briefs and deal-specific analyses with Sales and Product teams.

Location: Sunnyvale

Workplace: Onsite

Employment Type: Full time

Job Function: Solutions Engineering & Sales Engineering

Seniority: Mid level

Key Responsibilities

•Design standardized benchmark suites for inference workloads to enable fair, reproducible comparisons.
•Build and continuously update competitive pricing intelligence across inference providers and enterprise contract structures.
•Monitor GPU optimization communities and evaluate how kernel fusions, flash-attention variants, and quantization techniques impact performance ceilings.
•Synthesize industry announcements and benchmarking findings into actionable briefs for Sales and Product teams.
•Partner with Sales and collaborate with Product and Engineering on deal-specific analyses and competitive gap/advantage identification.

Key Requirements

•Deep practical experience with open-source inference frameworks such as vLLM, SGLang, or TensorRT-LLM.
•5+ years of experience in ML systems, ML research engineering, or high-performance computing.
•Strong understanding of LLM inference economics including tokens, throughput, latency, batch sizes, and precision trade-offs.
•Strong understanding of transformer architecture internals (attention mechanisms) and KV-cache management and how they affect memory/compute profiles.
•Self-directed and resourceful.

Experience:5+ yearsOpen source

Skills:Self-directedResourceful

Tech Stack:VLLMSGLangTensorRT-LLMCUDATriton

Company Brief

Cerebras

Designs and builds wafer-scale AI accelerators and systems for large-scale deep learning workloads, delivering specialized hardware and software to accelerate model training and inference for enterprises and research institutions.

Industry: Hardware Devices

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Headquarters: Sunnyvale, United States

Founded: 2016

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

Cerebras

3 months ago

Senior Performance Engineer, Inference

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 3 hours agoStatus: Live

Job Summary

Location: Sunnyvale

Workplace: Onsite

Employment Type: Full time

Job Function: Solutions Engineering & Sales Engineering

Seniority: Mid level

Key Responsibilities

•Design standardized benchmark suites for inference workloads to enable fair, reproducible comparisons.
•Build and continuously update competitive pricing intelligence across inference providers and enterprise contract structures.
•Monitor GPU optimization communities and evaluate how kernel fusions, flash-attention variants, and quantization techniques impact performance ceilings.
•Synthesize industry announcements and benchmarking findings into actionable briefs for Sales and Product teams.
•Partner with Sales and collaborate with Product and Engineering on deal-specific analyses and competitive gap/advantage identification.

Key Requirements

•Deep practical experience with open-source inference frameworks such as vLLM, SGLang, or TensorRT-LLM.
•5+ years of experience in ML systems, ML research engineering, or high-performance computing.
•Strong understanding of LLM inference economics including tokens, throughput, latency, batch sizes, and precision trade-offs.
•Strong understanding of transformer architecture internals (attention mechanisms) and KV-cache management and how they affect memory/compute profiles.
•Self-directed and resourceful.

Experience:5+ yearsOpen source

Skills:Self-directedResourceful

Tech Stack:VLLMSGLangTensorRT-LLMCUDATriton

Company Brief

Cerebras

Industry: Hardware Devices

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Headquarters: Sunnyvale, United States

Founded: 2016

Website LinkedIn