{"id":"4i2a7u304e","title":"Senior Software Engineer - Model Performance","posted_at":"2026-01-21T18:33:05.000Z","apply_url":"https://jobs.ashbyhq.com/inference/7a2963de-1b33-4dfc-b711-990faa93a6a5/application","locations":["San Francisco, CA"],"employment_type":"full_time","workplace_type":"on_site","seniority_level":null,"description_language":"en","source_name":"ashby","source_url":"https://jobs.ashbyhq.com/inference/7a2963de-1b33-4dfc-b711-990faa93a6a5","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":37.7949888,"location_lng":-122.3986798,"keywords":["infrastructure","architectures","architecture","Collaborate","distributed","performance","competitive","engineering","end-to-end","production","Kubernetes","efficient","standards","hardware","Platform","accuracy","PyTorch","latency","writing","vision","Growth","Python","GitHub","debug","LoRA","CUDA","GPU","C++","ML","AI","C+"],"company":{"name":"Inference","logo_url":"https://img.logo.dev/inference.ai?token=pk_fWx5G5QrQMm-0Ud8BW3mBg&size=64&format=png","description":"Inference operates a real-time marketplace that connects developers with spare GPU capacity across a distributed network of data centers.","website_url":"https://www.inference.ai/","linkedin_url":null,"glassdoor_url":null,"x_url":"https://x.com/Inference_ai","instagram_url":null,"youtube_url":null,"github_url":null,"huggingface_url":null,"tiktok_url":null,"crunchbase_url":"https://www.crunchbase.com/organization/inference-ai","facebook_url":null,"employee_count_range":"11-50","employee_count":null,"founded_year":2023,"headquarters":{"address":"530 Lytton Avenue, Palo Alto, CA, United States","city":"Palo Alto, CA","country":"US","lat":37.4443293,"lng":-122.1598465},"industry":"other","company_type":"startup","total_funding_usd":4000000,"locations":["San Francisco, CA"]}}