{"id":"u63u0987a8","title":"Member of Technical Staff, Exceptional Generalist (Remote)","posted_at":"2026-01-22T09:56:22.000Z","apply_url":"https://jobs.ashbyhq.com/inferact/f0d2619d-28e0-4b25-8d30-3ac555071abb/application","locations":["Remote"],"employment_type":"full_time","workplace_type":"remote","seniority_level":null,"description_language":"en","source_name":"ashby","source_url":"https://jobs.ashbyhq.com/inferact/f0d2619d-28e0-4b25-8d30-3ac555071abb","salary":null,"job_summary":null,"job_description":null,"visa_sponsorship":null,"experience_years_min":null,"job_address":null,"job_city":null,"job_state":null,"job_country":null,"location_lat":null,"location_lng":null,"keywords":["infrastructure","architectures","communication","architecture","Collaborate","distributed","performance","competitive","engineering","end-to-end","monitoring","production","Kubernetes","automation","Diffusion","hardware","Flexible","PyTorch","latency","design","global","Python","teams","local","CUDA","GPU","C++","ML","AI","C+"],"company":{"name":"Inferact","logo_url":"https://www.google.com/s2/favicons?domain=inferact.ai&sz=64","description":"Inferact is a technology company founded by the creators of vLLM that develops and optimizes the vLLM inference engine to improve the speed and cost-efficiency of running AI models across diverse hardware.","website_url":"https://inferact.ai","linkedin_url":"https://www.linkedin.com/company/inferact","glassdoor_url":null,"x_url":"https://x.com/inferact","instagram_url":null,"youtube_url":null,"github_url":null,"huggingface_url":"https://huggingface.co/Inferact","tiktok_url":null,"crunchbase_url":null,"facebook_url":null,"employee_count_range":"11-50","employee_count":null,"founded_year":2025,"headquarters":{"address":null,"city":"San Francisco, CA","country":"US","lat":37.7879363,"lng":-122.4075201},"industry":"other","company_type":"startup","total_funding_usd":150000000,"locations":["San Francisco, CA"]}}