{"id":23903,"url":"https://alion.io/job/cerebras-staff-software-engineer-gpu-inference","title":"Staff Software Engineer, GPU Inference","company":{"id":31,"name":"Cerebras Systems","domain":"cerebras.ai","url":"https://alion.io/company/cerebras-systems","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":73,"open_postings":26,"ghost_share":0,"stale_share":0.885,"repost_share":0,"time_to_fill_p50_days":80,"computed_at":"2026-10-16T05:45:00Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"staff","employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Toronto, Canada","Sunnyvale, United States"],"countries":["CA","US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":131000,"max_usd":268000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":18},"experience_years_min":8,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"C++","optional":false},{"name":"Cerebras","optional":false},{"name":"CI/CD","optional":false},{"name":"Edge AI","optional":false},{"name":"Kubernetes","optional":false},{"name":"KV Cache","optional":false},{"name":"Linux","optional":false},{"name":"Multimodal AI","optional":false},{"name":"OpenAI","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"PyTorch C++","optional":false},{"name":"Quantization","optional":false},{"name":"ROCm","optional":false},{"name":"SGLang","optional":false},{"name":"TensorRT-LLM","optional":false},{"name":"Triton","optional":false},{"name":"Triton Inference Server","optional":false},{"name":"vLLM","optional":false},{"name":"CUDA","optional":true},{"name":"CUDA Toolkit","optional":true},{"name":"Mixture of Experts","optional":true},{"name":"TensorRT","optional":true}],"status":"closed","first_seen_at":"2026-07-28T15:19:52Z","employer_posted_date":"2026-07-28","last_verified_at":"2026-10-16T22:12:14Z","board_verified":false,"closed_at":"2026-10-16T22:12:14Z","days_open":80,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":80},"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. \nThis 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.\nCerebras 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.\nAbout the Role\nCerebras 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.\nWe 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.\nYou 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.\nResponsibilities\nProductionize 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.\n\nOwn 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.\n\nDrive 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.\n\nImprove 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.\n\nOptimize 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.\n\nDebug 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.\n\nEnsure numerical correctness. Build validation and regression infrastructure for model quality, numerical accuracy, precision changes, quantization, determinism, and compatibility across software and hardware releases.\n\nBuild 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.\n\nMinimum Qualifications\n8+ years of software engineering experience, including substantial individual-contributor ownership of complex production systems.\n\nExperience building, operating, or optimizing production inference systems for large language models, multimodal models, or similarly demanding GPU workloads.\n\nStrong programming ability in C++ and Python, including experience with multithreading, concurrency, memory management, and performance-sensitive software.\n\nHands-on experience with a high-performance model-serving framework such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, or an equivalent internally developed system.\n\nStrong understanding of GPU execution and performance, including asynchronous execution, memory movement, synchronization, kernel launches, communication overhead, and profiling methodology.\n\nExperience debugging distributed systems across multiple layers rather than treating the serving framework or accelerator runtime as a black box.\n\nExperience with Linux, containers, Kubernetes or comparable orchestration systems, observability, CI/CD, and operating latency-sensitive services in production.\n\nAbility to design rigorous benchmarks, interpret noisy performance results, identify bottlenecks, and translate findings into production improvements.\n\nStrong communication and technical leadership skills, with a demonstrated ability to drive ambiguous cross-functional projects to completion.\n\nBachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related discipline, or equivalent practical experience.\n\nPreferred Qualifications\nExperience with AMD Instinct accelerators and the ROCm ecosystem, including HIP, RCCL, rocprofiler, AMD SMI, AITER, hipBLASLt, Composable Kernel, or related libraries and tools.\n\nDeep CUDA experience that demonstrates an ability to transfer GPU systems knowledge across accelerator platforms.\n\nExperience modifying or contributing to vLLM, SGLang, PyTorch, Triton, TensorRT-LLM, or another open-source ML systems project.\n\nExperience optimizing prefill-heavy or disaggregated prefill/decode inference architectures.\n\nUnderstanding of KV-cache transfer, prefix caching, continuous batching, chunked prefill, request scheduling, and memory-aware admission control.\n\nExperience with multi-GPU and multi-node inference, including tensor parallelism, pipeline parallelism, expert parallelism, RDMA, collective communication, and failure handling.\n\nExperience optimizing Mixture-of-Experts or multimodal models.\n\nKnowledge of GPU kernel optimization, operator fusion, graph capture, attention kernels, GEMM tuning, and communication/computation overlap.\n\nExperience with reduced-precision inference and quantization formats such as BF16, FP8, FP4, INT8, or INT4, including validation of their numerical and model-quality effects.\n\nExperience building numerical-comparison, determinism, model-validation, or performance-regression test systems.\n\nExperience collaborating directly with accelerator vendors, framework maintainers, or open-source communities.\n\nWhy Join Cerebras\nPeople who are serious about software make their own hardware. At Cerebras, we have built a breakthrough architecture that is unlocking new opportunities for the AI industry. With dozens of model releases and rapid growth, we’ve reached an inflection point in our business. Members of our team tell us there are five main reasons they joined Cerebras:\nBuild a breakthrough AI platform beyond the constraints of the GPU.\n\nPublish and open source their cutting-edge AI research.\n\nWork on one of the fastest AI supercomputers in the world.\n\nEnjoy job stability with startup vitality.\n\nOur simple, non-corporate work culture that respects individual beliefs.\n\nFind out more about what it's like to work at Cerebras here!\nApply today and become part of the forefront of groundbreaking advancements in AI!\nCerebras 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.\nThis website or its third-party tools process personal data. For more details, click here to review our CCPA disclosure notice.","description_format":"text","description_chars":7905,"description_truncated":false,"requirements":{"experience_years_min":8,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":["Continuous learning"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"},{"name":"Canada","iso":"CA","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Processors, MCUs & AI Chips","Servers & Data Center Hardware","AI Compute & Inference","AI Chips & Accelerators"],"lifecycle":[{"event":"open","at":"2026-07-28T15:19:52Z"},{"event":"close","at":"2026-10-16T22:12:14Z"}],"visa":[{"country":"CA","licensed_sponsor":true,"evidence":"Positions approved through LMIA in 12 months: 2","filings_12m":2,"filings_prev_12m":8,"green_card_filings_12m":null,"median_offered_wage_usd":null,"route":"High Wage; Global Talent Stream","cap_exempt":false,"checked_at":"2026-10-03T21:10:52+00:00","sources":["ESDC: employers issued a positive LMIA"],"filings_for_role_12m":2}],"liveness":null,"pay":null,"html_url":"https://alion.io/job/cerebras-staff-software-engineer-gpu-inference","json_url":"https://alion.io/job/cerebras-staff-software-engineer-gpu-inference.json","meta":{"generated_at":"2026-10-17T00:40:28Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":921,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-18T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":31},"rest":"https://alion.io/mcp/rest/get_company?id=31"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcerebras-staff-software-engineer-gpu-inference"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fcerebras-staff-software-engineer-gpu-inference"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fcerebras-staff-software-engineer-gpu-inference"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/cerebras-staff-software-engineer-gpu-inference\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcerebras-staff-software-engineer-gpu-inference"}]}