{"id":2785037,"url":"https://alion.io/job/nvidia-deep-learning-solution-architect","title":"Deep Learning Solution Architect","company":{"id":6,"name":"NVIDIA","domain":"nvidia.com","url":"https://alion.io/company/nvidia","size_band":"5000+","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workday","truth_index":{"grade":"B","score":82,"open_postings":592,"ghost_share":0.019,"stale_share":0.66,"repost_share":0.034,"time_to_fill_p50_days":33,"computed_at":"2026-10-17T05:46:00Z"}},"role":"Solutions","role_family":"Solutions","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":["Beijing, China","Shanghai, China"],"countries":["CN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":51000,"max_usd":122000,"period":"year","method":"global_role_cell_scaled_by_country","sample_n":1519},"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"RAG","optional":false},{"name":"Docker","optional":true},{"name":"Fine-tuning","optional":true},{"name":"Hugging Face","optional":true},{"name":"Kubernetes","optional":true},{"name":"KV Cache","optional":true},{"name":"LLM","optional":true},{"name":"Megatron-LM","optional":true},{"name":"NVIDIA NeMo","optional":true},{"name":"PyTorch","optional":true},{"name":"Quantization","optional":true},{"name":"Transformers","optional":true}],"status":"live","first_seen_at":"2026-04-04T00:00:00Z","employer_posted_date":"2026-04-04","last_verified_at":"2026-10-17T21:30:23Z","board_verified":true,"closed_at":null,"days_open":196,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":196},"description":"NVIDIA are seeking dynamic Solution Architects with specialized expertise in training Large Language Models (LLMs), implementing RAG workflows, and agentic inference. You will leverage the full NVIDIA software & hardware ecosystem to design, optimize, and deliver production-grade generative AI solutions for enterprise customers. With competitive salaries and a generous benefits package, we are widely considered to be one of the world’s most desirable employers! We have some of the most forward-thinking and hardworking people in the world working for us and, due to outstanding growth, our best-in-class engineering teams are rapidly growing. If you're a creative and autonomous person with a real passion for technology, we want to hear from you.\nWhat You Will Be Doing:\nArchitect end-to-end solutions focused on LLM pretraining, fine-tuning, high-performance inference, RAG workflows, and agentic inference orchestration using NVIDIA’s hardware and software platforms.\n\nCollaborate with customers to understand their LLM-related business challenges and design tailored solutions aligned with the NVIDIA ecosystem.\n\nLead LLM training, distributed optimization, and performance tuning to achieve optimal throughput, latency, and memory efficiency.\n\nDesign and integrate RAG workflows and agentic inference pipelines into customer systems; provide technical guidance on best practices.\n\nCollaborate with NVIDIA engineering teams to provide feedback and support pre-sales technical activities (workshops, demos).\n\nWhat We Need to See:\nMaster’s / Ph.D. in Computer Science, Artificial Intelligence, or equivalent experience.\n\n4+ years hands-on experience in AI, focusing on open-source LLM training, fine-tuning, and production inference optimization.\n\nDeep understanding of mainstream LLM architectures and proficiency in LLM customization via PyTorch, Hugging Face Transformers.\n\nSolid knowledge of GPU computing, cluster architecture, and distributed parallel training/inference for LLMs.\n\nCompetency in agentic inference design and using AI agents to solve business challenges.\n\nStrong communication skills, able to articulate complex technical concepts to technical and non-technical stakeholders.\n\nWays to Stand Out from the Crowd:\nHands-on experience with NVIDIA’s generative AI ecosystem (TRT-LLM, Megatron-LM, NVIDIA NeMo).\n\nAdvanced skills in LLM optimization (quantization, KV Cache tuning, memory footprint reduction).\n\nExperience with Docker, Kubernetes for containerized LLM and agent workflow deployment on-prem.\n\nIn-depth knowledge of multi-GPU parallelism and large-scale GPU cluster management.\n\n#deeplearning","description_format":"text","description_chars":2629,"description_truncated":false,"requirements":{"experience_years_min":4,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"master","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Processors, MCUs & AI Chips","Servers & Data Center Hardware","Computer Components","AI Chips & Accelerators"],"lifecycle":[{"event":"open","at":"2026-10-17T13:59:34Z"}],"visa":[],"liveness":{"score":12,"band":"cold","label":"Long shot","p_open":1,"p_active":0.431,"p_room":0.28,"age_days":196,"expected_fill_days":33,"reasons":["conf:0","win:tail","crowd:brand"],"computed_at":"2026-10-17T21:58:00Z"},"pay":null,"html_url":"https://alion.io/job/nvidia-deep-learning-solution-architect","json_url":"https://alion.io/job/nvidia-deep-learning-solution-architect.json","meta":{"generated_at":"2026-10-17T21:58:00Z","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":6851,"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":6},"rest":"https://alion.io/mcp/rest/get_company?id=6"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fnvidia-deep-learning-solution-architect"},{"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%2Fnvidia-deep-learning-solution-architect"},{"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%2Fnvidia-deep-learning-solution-architect"},{"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/nvidia-deep-learning-solution-architect\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fnvidia-deep-learning-solution-architect"}]}