Software Engineer, GPU Inference

Cerebras; Toronto; On-site; CAD 140,000 - 210,000; Full time

Job summary

Cerebras Systems is hiring a Software Engineer to productionize and optimize our GPU serving stack, spanning API services, vLLM, the ROCm software stack, and rack-scale AMD GPU infrastructure. You will write production code, establish operational practices for a new accelerator fleet, and drive improvements in time to first token, throughput, tail latency, and capacity efficiency.

This is a hands-on role requiring deep debugging across application, runtime, distributed systems, and hardware

Qualifications

• 5+ years of software engineering experience with ownership of complex production systems.
• Experience building, operating, or optimizing production inference systems for large language models or similar GPU workloads.
• Strong programming ability in C++ and Python, including multithreading and performance-sensitive software.
• Hands-on experience with a high-performance model-serving framework (vLLM, SGLang, TensorRT-LLM, Triton or similar).
• Strong understanding of GPU execution, memory movement, synchronization, and profiling methodologies.
• Experience debugging distributed systems across multiple layers, not just the serving framework.
• Experience with Linux, containers, Kubernetes, observability, CI/CD, and latency-sensitive services in production.
• Ability to design benchmarks, interpret results, and translate into production improvements.
• Strong communication and leadership skills with cross-functional collaboration.
• Bachelor’s degree in related discipline or equivalent experience.

Responsibilities

• Productionize the GPU inference stack across API services, model-serving workers, vLLM, PyTorch, ROCm, and hardware infrastructure.
• Own deployment, upgrades, health checks, capacity management, and automated compatibility across driver, firmware, runtime, and containers.
• Define SLIs/SLIs for GPU-backed inference; improve fault isolation and incident response.
• Profile and optimize time to first token, throughput, tail latency, memory efficiency, and rack-level capacity.
• Tune scheduling, batching, KV-cache management, and parallelism for efficient model serving.
• Diagnose failures and performance regressions across application, runtime, and hardware layers.
• Build validation, determinism, and regression infrastructure for model quality and numerical correctness.
• Develop benchmarks, workload replay tools, and dashboards; enforce repeatable engineering processes.

Skills

C++ programming

Python programming

Distributed systems debugging

Communication & leadership

Performance optimization

Problem solving

Education

Bachelor’s degree in Computer Science/Engineering

Tools

vLLM

SGLang

PyTorch

Triton Inference Server

ROCm

Kubernetes

Linux

CI/CD

HIP

Job description

Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. This architecture allows Cerebras to deliver industry-leading training and inference speeds; over 10 times faster than GPU-based hyperscale cloud inference services. This order of magnitude increase in speed is transforming the user experience of AI applications, unlocking real-time iteration and increasing intelligence via additional agentic computation. Cerebras works with the leading model labs, global enterprises, and cutting-edge AI-native startups. OpenAI recently announced a multi-year partnership with Cerebras, to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference.

About The Role

Cerebras is building a new generation of disaggregated AI inference systems that combine GPU-accelerated prefill with ultra-fast decode on the Cerebras Wafer-Scale Engine.

We are hiring a Software Engineer to productionize and optimize our GPU serving stack, working across our custom inference APIs, the vLLM serving runtime, the AMD ROCm software stack, and rack-scale AMD GPU infrastructure, to make this new serving path reliable, numerically correct, observable, and exceptionally performant.

You will write production code, establish operational practices for a new accelerator fleet, and drive improvements in time to first token, throughput, tail latency, and capacity efficiency. This is a hands-on role requiring deep debugging and optimization across application, runtime, distributed systems, and hardware layers.

Responsibilities

• Productionize the GPU inference stack. Design, build, deploy, and maintain the complete GPU prefill path, spanning API services, model-serving workers, vLLM, PyTorch, ROCm, GPU nodes, networking, and rack-scale infrastructure.
• Own GPU operational readiness. Establish deployment, upgrade, rollback, health-checking, capacity-management, and failure-recovery practices for the AMD GPU fleet. Build automation that makes driver, firmware, runtime, model, and container compatibility explicit and reproducible.
• Drive reliability in production. Define service-level indicators and objectives for GPU-backed inference. Improve fault isolation, graceful degradation, automated recovery, incident response, and post-incident remediation across the serving stack.
• Improve inference performance. Profile and optimize time to first token, request throughput, tokens per second per GPU, tail latency, GPU utilization, memory efficiency, and rack-level capacity under representative production workloads.
• Optimize model-serving behavior. Tune and improve scheduling, continuous batching, prefix caching, KV-cache management, tensor and expert parallelism, request admission, quantization, graph execution, and distributed communication.
• Debug across system layers. Diagnose complex failures and performance regressions across application code, vLLM, PyTorch, ROCm/HIP, collective communication libraries, kernels, drivers, firmware, networking, and hardware.
• Ensure numerical correctness. Build validation and regression infrastructure for model quality, numerical accuracy, precision changes, quantization, determinism, and compatibility across software and hardware releases.
• Build performance and correctness infrastructure. Develop representative benchmarks, workload replay tools, profiling automation, release qualification, dashboards, and regression gates. Turn one-off investigations into repeatable engineering systems.

Minimum Qualifications

• 5+ years of software engineering experience, including substantial individual-contributor ownership of complex production systems.
• Experience building, operating, or optimizing production inference systems for large language models, multimodal models, or similarly demanding GPU workloads.
• Strong programming ability in C++ and Python, including experience with multithreading, concurrency, memory management, and performance-sensitive software.
• Hands-on experience with a high-performance model-serving framework such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, or an equivalent internally developed system.
• Strong understanding of GPU execution and performance, including asynchronous execution, memory movement, synchronization, kernel launches, communication overhead, and profiling methodology.
• Experience debugging distributed systems across multiple layers rather than treating the serving framework or accelerator runtime as a black box.
• Experience with Linux, containers, Kubernetes or comparable orchestration systems, observability, CI/CD, and operating latency-sensitive services in production.
• Ability to design rigorous benchmarks, interpret noisy performance results, identify bottlenecks, and translate findings into production improvements.
• Strong communication and technical leadership skills, with a demonstrated ability to drive ambiguous cross-functional projects to completion.
• Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related discipline, or equivalent practical experience.

Preferred Qualifications

• Experience with AMD Instinct accelerators and the ROCm ecosystem, including HIP, RCCL, rocprofiler, AMD SMI, AITER, hipBLASLt, Composable Kernel, or related libraries and tools.
• Deep CUDA experience that demonstrates an ability to transfer GPU systems knowledge across accelerator platforms.
• Experience modifying or contributing to vLLM, SGLang, PyTorch, Triton, TensorRT-LLM, or another open-source ML systems project.
• Experience optimizing prefill-heavy or disaggregated prefill/decode inference architectures.
• Understanding of KV-cache transfer, prefix caching, continuous batching, chunked prefill, request scheduling, and memory-aware admission control.
• Experience with multi-GPU and multi-node inference, including tensor parallelism, pipeline parallelism, expert parallelism, RDMA, collective communication, and failure handling.
• Experience optimizing Mixture-of-Experts or multimodal models.
• Knowledge of GPU kernel optimization, operator fusion, graph capture, attention kernels, GEMM tuning, and communication/computation overlap.
• Experience with reduced-precision inference and quantization formats such as BF16, FP8, FP4, INT8, or INT4, including validation of their numerical and model-quality effects.
• Experience building numerical-comparison, determinism, model-validation, or performance-regression test systems.
• Experience collaborating directly with accelerator vendors, framework maintainers, or open-source communities.

Why Join Cerebras

About

• Build a breakthrough AI platform beyond the constraints of the GPU.
• Publish and open source their cutting-edge AI research.
• Work on one of the fastest AI supercomputers in the world.
• Enjoy job stability with startup vitality.
• Our simple, non-corporate work culture that respects individual beliefs.

Find out more about what it's like to work at Cerebras here!

Cerebras Systems is committed to creating an equal and diverse environment and is proud to be an equal opportunity employer. We celebrate different backgrounds, perspectives, and skills. We believe inclusive teams build better products and companies. We try every day to build a work environment that empowers people to do their best work through continuous learning, growth and support of those around them.

This website or its third-party tools process personal data. For more details, click here to review our CCPA disclosure notice.