{"id":126351,"url":"https://alion.io/job/near-llm-inference-engineer","title":"LLM Inference Engineer","company":{"id":17157,"name":"Near","domain":"near.ai","url":"https://alion.io/company/near","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greenhouse","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":null,"work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Francisco, United States"],"countries":["US"],"hiring_countries":["US"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":143000,"max_usd":312000,"period":"year","method":"role_country_seniority_unknown","sample_n":4027},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"LLM","optional":false},{"name":"Machine Learning","optional":false},{"name":"PyTorch","optional":false},{"name":"SGLang","optional":false},{"name":"TensorRT","optional":false},{"name":"Triton","optional":false},{"name":"vLLM","optional":false}],"status":"live","first_seen_at":"2026-07-06T11:30:42Z","employer_posted_date":"2026-08-26","last_verified_at":"2026-10-17T21:53:12Z","board_verified":true,"closed_at":null,"days_open":103,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":102},"description":"Locations: San Francisco or Remote\nAbout The Role\nThe NEAR AI team is building decentralized and confidential machine learning infrastructure to enable user-owned AI. Our mission is to build highly scalable and efficient infrastructure for open-source AI at a global scale.\nWe are specifically seeking an expert in high-performance LLM serving systems and inference optimization. In this role, you will push the boundaries of how large language models are served.\nWhat You'll Be Doing\nArchitect and maintain production high-traffic LLM serving systems.\nOptimize throughput, latency, and cost for leading open-source LLMs.\nWhat We're Looking For\nStrong hands-on experience in LLM inference, with expertise debugging and optimizing major inference engines such as SGLang, vLLM, or TensorRT.\nDeep knowledge of state-of-the-art GPU architectures, and effectively exploit them using PyTorch, Triton, CuTe, CUDA, etc.\nProven track record in designing and maintaining end-to-end high-traffic LLM serving systems.\nStrong problem-solving skills and ability to communicate technical ideas clearly.\nWe'd Love If You Have\nExperience with Trusted Execution Environments (TEE).\nActive contributor to open-source LLM inference engines.\nPlease let us know if you require any special requirements for your interview and we'll do our best to accommodate.","description_format":"text","description_chars":1336,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["AI Agents"],"lifecycle":[{"event":"open","at":"2026-07-06T11:30:42Z"}],"visa":[],"liveness":{"score":11,"band":"cold","label":"Long shot","p_open":1,"p_active":0.381,"p_room":0.28,"age_days":102,"expected_fill_days":38,"reasons":["conf:0","win:tail","crowd:"],"computed_at":"2026-10-17T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/near-llm-inference-engineer","json_url":"https://alion.io/job/near-llm-inference-engineer.json","meta":{"generated_at":"2026-10-17T23:49:04Z","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":2223,"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":17157},"rest":"https://alion.io/mcp/rest/get_company?id=17157"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fnear-llm-inference-engineer"},{"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%2Fnear-llm-inference-engineer"},{"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%2Fnear-llm-inference-engineer"},{"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/near-llm-inference-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fnear-llm-inference-engineer"}]}