AI Inference Core - Software Integration Engineer
Cerebras · Sunnyvale, CA
About this role
## About Cerebras Cerebras Systems builds the world’s largest AI chip—**56x larger than GPUs**—enabling **industry-leading training and inference speeds** (over **10x faster** than GPU-based hyperscale cloud inference services). This speed increase is transforming AI application experiences by enabling **real-time iteration** and more **agentic computation**. Cerebras works with leading model labs, global enterprises, and AI-native startups. OpenAI recently announced a multi-year partnership with Cerebras to deploy **750 megawatts** of scale for ultra high-speed inference. --- ## About the Role We’re looking for a **Software Integration Engineer** to join the **AI Inference Core** team. This team sits at the intersection of **AI infrastructure, distributed systems, compilers, runtimes, kernels, and hardware/software co-design**—the “**Innovation Engine**” for turning inference ideas into working reality. > **Note:** This is a **special task force** role—not a typical engineering role. ### What makes this role different - **Zero-to-one mission:** Take incomplete ideas and early prototypes to **working, validated capabilities**. - **Cross-stack complexity:** Integrate across **AI frameworks, runtimes, compilers, kernels, distributed systems, infrastructure, and hardware**. - **Accelerated cadence:** Expect focused daily syncs, rapidly changing priorities, and intense integration periods. - **Comfort on the hot seat:** Own outcomes when the path is unclear; make decisions with incomplete information. - **Bias for action:** “No process, no documentation—just get stuff done,” then turn learnings into better automation/diagnostics/docs. - **Team multiplier:** Push work forward while raising the pace, clarity, and effectiveness of the team. We welcome **exceptional junior engineers** with strong fundamentals, curiosity, ownership, and persistence. --- ## What You’ll Do - Turn new inference ideas and features into **integrated, working capabilities** across the Cerebras platform. - Take high-value projects from **zero to one** (prototype → working, validated capability). - Integrate and validate software components spanning **AI frameworks, runtime, compiler, kernels, distributed systems, and hardware**. - Drive cross-component projects from **problem definition → integration → validation → release readiness**. - Collaborate with software and hardware engineers to make **co-design trade-offs** and resolve system-level issues. - Investigate and debug difficult failures across **large-scale AI workloads** and **hardware/software boundaries**. - Work effectively on accelerated timelines while keeping **risks, dependencies, and decisions visible**. - Participate in focused daily syncs and drive ambiguous situations to concrete outcomes. - Identify bottlenecks, failure modes, edge cases, and integration gaps affecting **correctness, performance, or delivery**. - Capture lessons from urgent work to make future integrations faster and less chaotic. - Help teammates move faster by closing difficult problems together. --- ## Minimum Skills & Qualifications - Strong software engineering fundamentals; programming ability in **Python, C++, Go, or similar**. - Experience with **software/hardware co-design** and/or **hardware accelerators, compilers, kernels, runtimes, or low-level systems**. - Experience debugging **complex systems**, **distributed software**, or **large-scale compute clusters**. - Experience with **AI infrastructure**, **model d
Listing freshness
CronJobs last confirmed this listing 58m ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.