# Senior Performance Engineer, Inference

**Company:** [Cerebras Systems](https://hotfix.jobs/companies/cerebras-systems)
**Location:** Sunnyvale, CA
**Role:** ML Engineering
**Experience:** 5+ years
**Skills:** vLLM, Sglang, Tensorrt-Llm, CUDA, Triton, Kv-Cache, Quantization, Flash-Attention, Transformers, Llm Inference
**Posted:** 2026-04-17

> Senior Performance Engineer benchmarks Cerebras inference performance against competitors for real workloads, measuring metrics like tokens/second and TCO, while modeling competitor pricing to inform sales strategies. Requires 5+ years in ML systems and deep expertise in open-source inference stacks and transformer optimizations.

## Job Description

## Responsibilities
- Design standardized benchmark suites for inference workloads (code generation, summarization, multi-turn conversation, agentic tool use) that enable fair, reproducible comparisons.
- Stay current with GPU optimization communities (CUDA, Triton, TensorRT) and evaluate how new kernel fusions, flash-attention variants, and quantization techniques shift performance ceilings.
- Build and continuously update a competitive pricing model covering token-based pricing, throughput-based pricing, and enterprise contract structures across major inference providers.
- Monitor industry announcements, pricing changes, and new product launches. Synthesize findings into actionable briefs for the Sales and Product teams.
- Partner with Sales to build deal-specific competitive analyses showing total cost of ownership and performance advantages for enterprise prospects.
- Collaborate with Product and Engineering to identify where competitors are closing gaps or where Cerebras has underappreciated advantages.
- Track third-party benchmarking sources (Artificial Analysis, InferenceX) and ensure Cerebras is well-represented and accurately measured.

## Required Skills & Qualifications
- Deep practical experience with state-of-the-art open-source inference frameworks like **vLLM**, **SGLang**, or **TensorRT-LLM**.
- Strong understanding of LLM inference economics: tokens, throughput, latency, batch sizes, precision trade-offs, and how these translate to customer cost.
- Strong understanding of transformer model architecture internals such as attention mechanisms (**MHA, MQA, GQA, MLA, DSA, MHA**) and KV-cache management, and how each affects memory and compute profiles.
- Self-directed and resourceful.

## Preferred
- Background in ML research (publications or significant open-source contributions) with a systems or efficiency focus.
- Contributions to open-source inference or kernel optimization projects.
- Excellent communication skills.

## Similar roles

- [Senior Applied Scientist](https://hotfix.jobs/jobs/3ae25509-6ddb-4378-a140-0b121812bdbf) - DAT Freight & Analytics - Seattle, WA - $183k – $226k/yr
- [Senior Machine Learning Engineer, Relevance and Personalization](https://hotfix.jobs/jobs/589feee3-05a3-4944-84df-8bd20d220687) - Airbnb - Remote - $200k – $235k/yr
- [Senior Machine Learning Engineer, Agent Oversight](https://hotfix.jobs/jobs/1f504a69-044f-47ab-872b-120a1706cd88) - Scale AI - San Francisco, CA - $216k – $270k/yr
- [Senior Software Engineer, Agent Oversight](https://hotfix.jobs/jobs/808ce719-6b16-4b6e-8887-8c8f8a780b75) - Scale AI - San Francisco, CA - $216k – $270k/yr
- [Senior Software Engineer, AI Infrastructure](https://hotfix.jobs/jobs/dd1c3420-6c0a-47ed-a1a7-de401bdf506c) - Ambient.ai - Redwood City, CA - $168k – $205k/yr

**Apply:** https://hotfix.jobs/jobs/602f2aaf-894b-481c-98bd-b0361f13a6f6
**Canonical:** https://hotfix.jobs/jobs/602f2aaf-894b-481c-98bd-b0361f13a6f6