{"id":3431565,"url":"https://alion.io/job/zenlayer-staff-software-engineer-llm-inference-platform","title":"Staff Software Engineer, LLM Inference Platform","company":{"id":180737,"name":"Zenlayer","domain":"zenlayer.com","url":"https://alion.io/company/zenlayer","size_band":"201-500","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"BambooHR","truth_index":{"grade":"A","score":87,"open_postings":3,"ghost_share":0,"stale_share":0.333,"repost_share":0,"time_to_fill_p50_days":75,"computed_at":"2026-11-06T05:58:05Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"staff","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Cupertino, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":177000,"max_usd":352000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":890},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWQ","optional":false},{"name":"CUDA","optional":false},{"name":"DeepSeek","optional":false},{"name":"GPTQ","optional":false},{"name":"HPC","optional":false},{"name":"KV Cache","optional":false},{"name":"LLM","optional":false},{"name":"Mixture of Experts","optional":false},{"name":"Quantization","optional":false},{"name":"Qwen","optional":false},{"name":"ROCm","optional":false},{"name":"SGLang","optional":false},{"name":"SLI/SLO/SLA","optional":false},{"name":"TensorRT-LLM","optional":false},{"name":"TPOT","optional":false},{"name":"Transformers","optional":false},{"name":"vLLM","optional":false},{"name":"TensorRT","optional":true}],"status":"closed","first_seen_at":"2026-10-29T00:46:44Z","employer_posted_date":"2026-10-29","last_verified_at":"2026-10-29T22:32:51Z","board_verified":false,"closed_at":"2026-10-29T22:32:51Z","days_open":0,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":0},"description":"About Zenlayer\nZenlayer is the first massively distributed edge cloud provider, operating 290+ Points of Presence across 70+ countries. With accolades including PTC “Best Networking Innovation”, “Outstanding Cloud, Data Center, or Interconnection Company”, and Inc. 5000, we enable businesses to deploy and run applications at the edge, thus reducing network latency to the end user. Zenlayer focuses on improving connections worldwide, all while nurturing a unique company culture that values service, growth, and trust. As a “Zenplayer”, you’ll be joining a community of success-driven team players that share the dream of powering a better-connected world.\nAbout the Role: \nAs the technical lead for inference performance, you will own end-to-end responsibility for the platform's Token Performance. For models ranging from hundreds of billions to trillions of parameters (including MoE), you will continuously reduce cost per million tokensand increase per-GPU Goodputwhile meeting TTFT/TPOT SLOs, andprove the gain from every optimization with reproducible data.\nWhat You Will Work On\n1. End-to-End Performance Attribution and Benchmarking\nEstablish a unified Token Performance metrics framework (TTFT, TPOT, Goodput, GPU utilization, per-token cost), and build load-testing benchmarks that reflect real production traffic (high concurrency, long context, multi-turn Agent workloads)\nPerform bottleneck attribution for models such as DeepSeek, Kimi, GLM, Qwen, and MiniMaxacross compute, memory bandwidth, communication, scheduling, and queuing, and let the data determinewhich layer is the dominant constraint\n2. Kernel-Level Inference Engine Optimization\nDive deep into the source code of vLLM/ SGLang/ TensorRT-LLM, customizing and contributing upstream on critical paths such as the scheduler, Continuous Batching, Chunked Prefill, CUDA Graph, and KV block management\nClearly define the responsibility boundary between the inference engine and orchestration layers such as Dynamo / llm-d, and reduce tail latency through request routing and load balancing\n3. PD Disaggregation and KV Cache Transfer\nLead the core design of Prefill-Decode disaggregation: the KV transfer path (NIXL/RDMA/UCX), transfer-compute overlap, and phase-aware autoscaling\nDefine the failure domains and recovery semantics of cross-instance KV transfer, and answer the key question: under which workloads doesPD disaggregation deliver gains, and under which does it make things slower\n4. MoEParallelism and Wide-EP\nDesign hybrid TP/PP/DP/EP parallelism strategies and quantify the trade-offs between EP and TP\nTackle expert load imbalance and All-to-All communication overhead, and drive Wide-EP into production\n5. Kernels and Quantization\nWrite and tune critical CUDA (and ROCm/HIP) operators: memory access optimization, kernel fusion, and Attention / MoE/ communication-related kernels\nBuild a closed-loop \"quantization - accuracy - throughput\" evaluation: the real-world gains and accuracy regressions of FP8/FP4/INT4/AWQ/GPTQ across different engines and hardware\nRequirements\nFirst-principles understanding of Transformer inference: the compute vs. memory-bound nature of Prefill and Decode, the KV Cache memory model, the differences among MHA/GQA/MLA, and how MoErouting constrains parallelism\nSource-level, in-depth experience with at least one mainstream inference engine, with real cases of identifyingand fixing bottlenecks in scheduling, kernel selection, or KV management\nCUDA kernel tuning skills (Nsight profiling, memory optimization, fusion, CUDA Graph) with hands-on practical experience\nBachelor’s degree in ComputerScience, Electrical/Computer Engineering, or related field (HPC systems, ML Systems).\nMinimum 6 years in systems/Performance Engineering, with at least 2-3 years directly on LLM or GPU performance work\nPreferred, but not required:\nExperience with Merged PRs in vLLM\nExperience operatingat cluster sale (hundredsto thousands of GPUs)","description_format":"text","description_chars":3950,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Data Centers & Colocation","Cloud Platforms (IaaS & PaaS)","CDN & Edge Delivery"],"lifecycle":[{"event":"open","at":"2026-10-29T00:46:44Z"},{"event":"close","at":"2026-10-29T22:32:51Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"green card filings: 1","filings_12m":0,"filings_prev_12m":2,"green_card_filings_12m":1,"median_offered_wage_usd":162500,"route":null,"cap_exempt":false,"checked_at":"2026-10-29T16:27:21+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)","US Department of Labor: PERM disclosure data (green cards)"],"filings_for_role_12m":0}],"liveness":null,"pay":null,"html_url":"https://alion.io/job/zenlayer-staff-software-engineer-llm-inference-platform","json_url":"https://alion.io/job/zenlayer-staff-software-engineer-llm-inference-platform.json","meta":{"generated_at":"2026-11-06T13:51:00Z","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":25482,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-07T00:00:00Z"}},"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":180737},"rest":"https://alion.io/mcp/rest/get_company?id=180737"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fzenlayer-staff-software-engineer-llm-inference-platform"},{"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%2Fzenlayer-staff-software-engineer-llm-inference-platform"},{"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%2Fzenlayer-staff-software-engineer-llm-inference-platform"},{"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/zenlayer-staff-software-engineer-llm-inference-platform\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fzenlayer-staff-software-engineer-llm-inference-platform"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3431565}},{"tool":"search_jobs","arguments":{"company":"zenlayer.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3431565},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}