{"id":449233,"url":"https://alion.io/job/pulse-software-engineer-inference","title":"Software Engineer, Inference","company":{"id":173587,"name":"Pulse","domain":"runpulse.com","url":"https://alion.io/company/pulse-3","size_band":"201-500","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"D","score":46,"open_postings":10,"ghost_share":0.9,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-23T05:54:15Z"}},"role":"Backend","role_family":"Backend","seniority":"middle","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 Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":150000,"max":230000,"currency":"USD","period":"year","gross":null,"usd_annual":230000},"salary_estimate":null,"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Computer Vision","optional":false},{"name":"NLP","optional":false},{"name":"OCR","optional":false},{"name":"C++","optional":true},{"name":"CUDA","optional":true},{"name":"Multimodal AI","optional":true},{"name":"Python","optional":true},{"name":"SLI/SLO/SLA","optional":true},{"name":"TensorRT","optional":true},{"name":"TensorRT-LLM","optional":true},{"name":"Tokenization","optional":true},{"name":"Triton","optional":true},{"name":"vLLM","optional":true}],"status":"live","first_seen_at":"2025-07-30T04:19:11Z","employer_posted_date":"2025-07-30","last_verified_at":"2026-10-23T23:26:41Z","board_verified":true,"closed_at":null,"days_open":450,"trust":{"level":"ghost","repost_count":0,"flags":["stale","company_stale"],"days_open":450},"description":"Overview\n\n Pulse is tackling one of the most persistent challenges in data infrastructure: extracting accurate, structured information from complex documents at scale. We have a breakthrough approach to document understanding that combines intelligent schema mapping with fine-tuned extraction models where legacy OCR and other parsing tools consistently fail.\nWe are a small, fast-growing team of engineers in San Francisco powering Fortune 100 enterprises, YC startups, public investment firms, and growth-stage companies. We are backed by tier 1 investors and growing quickly.\nWhat makes our tech special is our multi-stage architecture:\nLayout understanding with specialized component detection models\n\nLow-latency OCR models for targeted extraction\n\nAdvanced reading-order algorithms for complex structures\n\nProprietary table structure recognition and parsing\n\nFine-tuned vision-language models for charts, tables, and figures\n\nIf you are passionate about the intersection of computer vision, NLP, and data infrastructure, your work at Pulse will directly impact customers and shape the future of document intelligence.\nWhat we are looking for\n5 days in-office at our San Francisco office\n\nEager to learn and adapt quickly\n\nPrior startup or founding experience is a plus\n\nWhat we are looking for\n5 days in-office at our San Francisco office\n\nEager to learn and adapt quickly\n\nPrior startup or founding experience is a plus\n\nAbout the Role\n Specialize in low-latency, high-throughput inference for OCR and multimodal models. Own profiling, batching, and autoscaling across single-tenant and multi-tenant environments.\nResponsibilities\nBuild inference services with smart batching and caching\n\nOptimize kernels, tokenization, and model graphs\n\nEvaluate vLLM, TensorRT LLM, and Triton tradeoffs\n\nImplement autoscaling and admission control with clear SLOs\n\nOwn performance dashboards and capacity planning\n\nRequirements\n3+ years in performance engineering or ML systems\n\nStrong Python, plus C++ or CUDA exposure\n\nExperience with GPU profiling and model serving\n\nNice to have\nExperience reducing p95 and cost in production ML systems\n\nSponsorship\n Sponsorship available.\nCompensation and benefits\n Competitive base salary plus equity, performance-based bonus, relocation assistance for Bay Area moves, daily meal stipend, medical, vision, and dental coverage.","description_format":"text","description_chars":2360,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Equity","Relocation assistance"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":true,"industries":["Cybersecurity","Computer Vision","Information Security","Document AI"],"lifecycle":[{"event":"open","at":"2026-09-06T08:13:52Z"},{"event":"open","at":"2026-09-26T09:37:26Z"}],"visa":[],"liveness":{"score":4,"band":"cold","label":"Long shot","p_open":1,"p_active":0.15,"p_room":0.28,"age_days":450,"expected_fill_days":30,"reasons":["conf:1","stale_co","ghost","win:tail","crowd:"],"computed_at":"2026-10-23T05:54:15Z"},"pay":{"stated_usd_annual":230000,"is_top_pay":true},"html_url":"https://alion.io/job/pulse-software-engineer-inference","json_url":"https://alion.io/job/pulse-software-engineer-inference.json","meta":{"generated_at":"2026-10-24T00:23:04Z","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":541,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-25T00:00:00Z"}},"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":173587},"rest":"https://alion.io/mcp/rest/get_company?id=173587"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fpulse-software-engineer-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%2Fpulse-software-engineer-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%2Fpulse-software-engineer-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/pulse-software-engineer-inference\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fpulse-software-engineer-inference"}]}