{"id":2242987,"url":"https://alion.io/job/nebius-senior-applied-scientist-efficient-llm-inference-model-optimization","title":"Senior Applied Scientist, Efficient LLM Inference & Model Optimization","company":{"id":6364,"name":"Nebius","domain":"nebius.com","url":"https://alion.io/company/nebius","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greenhouse","truth_index":{"grade":"B","score":75,"open_postings":135,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-12T06:55:09Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"senior","employment_type":null,"work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Palo Alto, United States","San Francisco, United States"],"countries":["US"],"hiring_countries":["US"],"hiring_countries_total":1,"salary":{"min":195200,"max":262200,"currency":"USD","period":"year","gross":null,"usd_annual":262200},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"Knowledge Distillation","optional":false},{"name":"KV Cache","optional":false},{"name":"LLM","optional":false},{"name":"Machine Learning","optional":false},{"name":"Mixture of Experts","optional":false},{"name":"Model Distillation","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Quantization","optional":false},{"name":"Speculative Decoding","optional":false},{"name":"Triton","optional":false},{"name":"VLM","optional":false},{"name":"DPO","optional":true},{"name":"Post-training","optional":true},{"name":"RLAIF","optional":true},{"name":"RLHF","optional":true},{"name":"SFT","optional":true},{"name":"SGLang","optional":true},{"name":"Synthetic Data","optional":true},{"name":"TensorRT","optional":true},{"name":"TensorRT-LLM","optional":true},{"name":"vLLM","optional":true}],"status":"live","first_seen_at":"2026-07-22T22:53:48Z","employer_posted_date":"2026-10-08","last_verified_at":"2026-10-12T18:47:37Z","board_verified":true,"closed_at":null,"days_open":81,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":81},"description":"About Nebius:\nNebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure.\nBuilt by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI.\nListed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D.\nThe role \nNebius Token Factory is looking for scientists who can turn frontier LLM and VLM inference bottlenecks into research questions, conduct rigorous experiments, and translate their findings into production capabilities. You will own focused research and optimization projects, write strong code, and produce prototypes, publications, and technical artifacts that engineers can build on.\nYour research will span quantization, distillation, speculative decoding, KV-cache optimization, and model/runtime co-optimization, alongside inference engines and distributed inference architectures. You will investigate how these approaches interact, evaluate their trade-offs across model quality, latency, throughput, memory footprint, and cost per token, and work with engineering teams to bring promising results into production.\nYour responsibilities: \nLead research projects in efficient LLM and VLM inference, from hypotheses and experiments through ablations, prototypes, and production handoff.\nDevelop and evaluate methods spanning quantization, quantization-aware training (QAT), distillation, speculative decoding, KV-cache reuse, KV-cache compression, long-context inference, MoE routing, and model/runtime co-optimization.\nBuild prototypes using PyTorch, Triton, CUDA-adjacent tooling, or inference-serving frameworks, and collaborate with MLEs and platform engineers to turn them into production components.\nResearch LLM request routing and scheduling strategies, including cache-aware load balancing and prefill-decode disaggregation (PDD). Evaluate how queueing, KV-cache transfer, worker placement, and prefill/decode capacity allocation affect latency, throughput, and serving cost.\nInvestigate multi-node inference for dense and mixture-of-experts models, including wide expert parallelism (WideEP). Study expert placement, load imbalance, and computation/communication trade-offs, and use the findings to guide model and system architecture choices.\nDevelop rigorous evaluations covering quality, latency, throughput, numerical stability, memory footprint, tail latency, and cost per token. Compare serving architectures under consistent workload conditions and GPU budgets.\nWork with MLE, GPU kernel, backend infrastructure, product, and customer teams to select research priorities with measurable production impact.\nShare results through internal reports, technical blogs, papers, and open-source artifacts, and mentor engineers and scientists on experimental design, scientific rigor, and model/system trade-offs.\nMust-haves: \nA PhD in computer science, machine learning, ML systems, computer systems, computer architecture, electrical engineering, applied mathematics, or a closely related discipline.\nA strong publication record or equivalent research artifacts in ML, ML systems, efficient inference, model compression, quantization, distillation, serving systems, or related areas.\n\nStrong Python and PyTorch implementation skills, with the ability to turn ideas into experiments and working prototypes.\n\nDeep knowledge of LLMs, VLMs, transformer inference, decoding algorithms, model compression, quantization, and production-serving trade-offs.\n\nStrong experimental design skills covering ablations, baselines, metrics, statistical reasoning, and failure analysis.\n\nExcellent written and verbal communication.\n\nNice-to-haves: \nFirst-author publications at venues such as NeurIPS, ICML, ICLR, MLSys, ACL, EMNLP, ASPLOS, OSDI, SOSP, ISCA, or HPCA.\n\nExperience deploying ML models or inference optimizations in production.\n\nExperience with vLLM, SGLang, TensorRT-LLM, NVIDIA Dynamo, FlashAttention, FlashInfer, Triton, CUDA, or PyTorch internals.\n\nExperience applying post-training, SFT, DPO, RLHF, RLAIF, preference optimization, or synthetic data generation to inference quality or efficiency.\n\nOpen-source research artifacts, widely used benchmarks, technical blogs, or invited talks demonstrating contributions to efficient AI systems.\n\nResearch or implementation experience in one or more areas of distributed inference system architecture, such as LLM request routing, PDD, multi-node serving, or MoE expert parallelism, including WideEP.\nKey employee benefits in the US:\nHealth insurance: 100% company-paid medical, dental, and vision coverage for employees and families.\n\n401(k) plan: Up to 4% company match with immediate vesting.\n\nParental leave: 20 weeks paid for primary caregivers, 12 weeks for secondary caregivers.\n\nRemote work reimbursement: Up to $85/month for mobile and internet.\n\nDisability & life insurance: Company-paid short-term, long-term and life insurance coverage.\n\nPay Transparency\nWe offer competitive compensation and benefits packages. Actual compensation will be determined based on job-related factors, including experience, skills, qualifications, the level at which the candidate is hired, and geographic location, consistent with applicable law.\nBase Compensation Range\n$195,200—$262,200 USD\nBenefits & Perks:\nCompetitive compensation\nCareer growth and learning opportunities\nFlexibility and ownership\nCollaborative and innovative culture\nOpportunity to work on impactful AI projects\nInternational environment and talented teams\nWhat's it like to work at Nebius:\nFast moving - Bold thinking - Constant growth - Meaningful impact - Trust and real ownership - Opportunity to shape the future of AI \nEqual Opportunity Statement:\nNebius is an equal opportunity employer. We are committed to fostering an inclusive and diverse workplace and to providing equal employment opportunities in all aspects of employment. We do not discriminate on the basis of race, color, religion, sex (including pregnancy), national origin, ancestry, age, disability, genetic information, marital status, veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by applicable law.\nApplicants must be authorized to work in the country in which they apply and will be required to provide proof of employment eligibility as a condition of hire. \nIf you need accommodations during the application process, please let us know.","description_format":"text","description_chars":6858,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"phd","optional":false},"security_clearance":false,"languages":[]},"benefits":["Health insurance","Insurance coverage","Life insurance","Parental leave"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","Commerce","Education","Data Centers & Colocation"],"lifecycle":[{"event":"open","at":"2026-10-11T01:05:42Z"}],"visa":[],"liveness":{"score":8,"band":"cold","label":"Long shot","p_open":1,"p_active":0.276,"p_room":0.28,"age_days":81,"expected_fill_days":32,"reasons":["conf:0","stale_co","win:tail","crowd:brand"],"computed_at":"2026-10-12T06:55:09Z"},"pay":{"stated_usd_annual":262200,"is_top_pay":true},"html_url":"https://alion.io/job/nebius-senior-applied-scientist-efficient-llm-inference-model-optimization","json_url":"https://alion.io/job/nebius-senior-applied-scientist-efficient-llm-inference-model-optimization.json","meta":{"generated_at":"2026-10-12T19:12:32Z","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":31076,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-13T00:00:00Z"}},"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":6364},"rest":"https://alion.io/mcp/rest/get_company?id=6364"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fnebius-senior-applied-scientist-efficient-llm-inference-model-optimization"},{"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%2Fnebius-senior-applied-scientist-efficient-llm-inference-model-optimization"},{"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%2Fnebius-senior-applied-scientist-efficient-llm-inference-model-optimization"},{"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/nebius-senior-applied-scientist-efficient-llm-inference-model-optimization\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fnebius-senior-applied-scientist-efficient-llm-inference-model-optimization"}]}