{"id":3821775,"url":"https://alion.io/job/genesis-ai-inference","title":"Inference","company":{"id":1908459,"name":"Genesis AI","domain":"genesis.ai","url":"https://alion.io/company/genesis-ai","size_band":"501-1000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"A","score":95,"open_postings":17,"ghost_share":0,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":102,"computed_at":"2026-11-07T05:47:08Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Carlos, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"C++","optional":false},{"name":"CUDA","optional":false},{"name":"Python","optional":false},{"name":"Quantization","optional":false},{"name":"Rust","optional":false},{"name":"Triton","optional":false}],"status":"live","first_seen_at":"2026-04-30T18:38:45Z","employer_posted_date":"2026-04-30","last_verified_at":"2026-11-07T05:42:55Z","board_verified":true,"closed_at":null,"days_open":190,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":190},"description":"What You’ll Do\nBuild low-latency inference pipelines for on-device deployment, enabling real-time next-token and diffusion-based control loops in robotics\n\nDesign and optimize distributed inference systems on GPU clusters, pushing throughput with large-batch serving and efficient resource utilization\n\nImplement efficient low-level code (CUDA, Triton, custom kernels) and integrate it seamlessly into high-level frameworks\n\nOptimize workloads for both throughput (batching, scheduling, quantization) and latency (caching, memory management, graph compilation)\n\nDevelop monitoring and debugging tools to guarantee reliability, determinism, and rapid diagnosis of regressions across both stacks\n\nWhat You’ll Bring\nDeep experience in distributed systems, ML infrastructure, or high-performance serving (8+ years)\n\nProduction-grade expertise in Python, with strong background in systems languages (C++/Rust/Go)\n\nLow-level performance mastery: CUDA, Triton, kernel optimization, quantization, memory and compute scheduling\n\nProven track record scaling inference workloads in both throughput-oriented cluster environments and latency-critical on-device deployments\n\nSystem-level mindset with a history of tuning hardware-software interactions for maximum efficiency, throughput, and responsiveness","description_format":"text","description_chars":1292,"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":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Robotics AI","Robotic Components & Sensors","Foundation Models"],"lifecycle":[{"event":"open","at":"2026-11-05T17:29:47Z"}],"visa":[],"liveness":{"score":17,"band":"cold","label":"Long shot","p_open":1,"p_active":0.46,"p_room":0.36,"age_days":190,"expected_fill_days":102,"reasons":["conf:0","win:tail","crowd:"],"computed_at":"2026-11-07T05:47:08Z"},"pay":null,"html_url":"https://alion.io/job/genesis-ai-inference","json_url":"https://alion.io/job/genesis-ai-inference.json","meta":{"generated_at":"2026-11-07T09:19:32Z","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":7101,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-08T00:00:00Z"}},"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":1908459},"rest":"https://alion.io/mcp/rest/get_company?id=1908459"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fgenesis-ai-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%2Fgenesis-ai-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%2Fgenesis-ai-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/genesis-ai-inference\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fgenesis-ai-inference"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3821775}},{"tool":"search_jobs","arguments":{"company":"genesis.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3821775},"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"}}