Impress employers and recruiters.
Choose from hundreds of resume examples.

Target Resume Now

About the Role

Cerebras is developing new disaggregated AI inference systems that combine GPU-accelerated prefill with ultra-fast decode on the Cerebras Wafer-Scale Engine. This role involves productionizing and optimizing our GPU serving stack, working with custom inference APIs, the vLLM serving runtime, the AMD ROCm software stack, and rack-scale AMD GPU infrastructure to ensure reliability, numerical correctness, observability, and high performance. The position requires writing production code, establishing operational practices for a new accelerator fleet, and improving key performance metrics like time to first token, throughput, tail latency, and capacity efficiency. It is a hands-on role demanding deep debugging and optimization across application, runtime, distributed systems, and hardware layers.

Responsibilities

Productionize the GPU inference stack, including designing, building, deploying, and maintaining the complete GPU prefill path across API services, model-serving workers, vLLM, PyTorch, ROCm, GPU nodes, networking, and rack-scale infrastructure.
Own GPU operational readiness by establishing deployment, upgrade, rollback, health-checking, capacity-management, and failure-recovery practices for the AMD GPU fleet.
Build automation to ensure explicit and reproducible compatibility for drivers, firmware, runtimes, models, and containers.
Drive reliability in production by defining 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 by profiling and optimizing time to first token, request throughput, tokens per second per GPU, tail latency, GPU utilization, memory efficiency, and rack-level capacity under production workloads.
Optimize model-serving behavior by tuning scheduling, continuous batching, prefix caching, KV-cache management, tensor and expert parallelism, request admission, quantization, graph execution, and distributed communication.
Debug complex failures and performance regressions across application code, vLLM, PyTorch, ROCm/HIP, collective communication libraries, kernels, drivers, firmware, networking, and hardware.
Ensure numerical correctness by building 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, including benchmarks, workload replay tools, profiling automation, release qualification, dashboards, and regression gates.
Transform one-off investigations into repeatable engineering systems.

Requirements

8+ 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.

Skills

C++
Python
Multithreading
Concurrency
Memory Management
Performance-sensitive software
vLLM
SGLang
TensorRT-LLM
Triton Inference Server
GPU execution
GPU performance
Asynchronous execution
Memory movement
Synchronization
Kernel launches
Communication overhead
Profiling methodology
Distributed systems debugging
Linux
Containers
Kubernetes
Observability
CI/CD
Latency-sensitive services
Benchmarking
Performance analysis
Bottleneck identification
AMD Instinct accelerators
ROCm ecosystem
HIP
RCCL
rocprofiler
AMD SMI
AITER
hipBLASLt
Composable Kernel
CUDA
PyTorch
Prefill-heavy inference architectures
Disaggregated prefill/decode inference architectures
KV-cache transfer
Prefix caching
Continuous batching
Chunked prefill
Request scheduling
Memory-aware admission control
Multi-GPU inference
Multi-node inference
Tensor parallelism
Pipeline parallelism
Expert parallelism
RDMA
Collective communication
Mixture-of-Experts models
Multimodal models
GPU kernel optimization
Operator fusion
Graph capture
Attention kernels
GEMM tuning
Communication/computation overlap
Reduced-precision inference
Quantization formats (BF16, FP8, FP4, INT8, INT4)
Numerical comparison systems
Determinism test systems
Model validation systems
Performance regression test systems

Location

Remote

Work Type

Full-time

Experience Level

8+ years of software engineering experience
Individual-contributor ownership of complex production systems

Education Level

Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related discipline, or equivalent practical experience.

Benefits

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.
Simple, non-corporate work culture that respects individual beliefs.

About the Company

Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs, delivering industry-leading training and inference speeds.
Their architecture transforms the user experience of AI applications, unlocking real-time iteration and increasing intelligence via additional agentic computation.
Cerebras collaborates with leading model labs, global enterprises, and cutting-edge AI-native startups.
OpenAI has partnered with Cerebras to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference.

Equal Opportunity

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 strive to build a work environment that empowers people to do their best work through continuous learning, growth and support of those around them.