{"id":835760,"url":"https://alion.io/job/sazabi-software-engineer-agents","title":"Software Engineer, Agents","company":{"id":689362,"name":"Sazabi","domain":"sazabi.com","url":"https://alion.io/company/sazabi","size_band":"11-50","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":75,"open_postings":8,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-09-28T05:45:00Z"}},"role":"Backend","role_family":"Backend","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 Francisco, United States","New York, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":152000,"max_usd":318000,"period":"year","method":"role_country_seniority_unknown","sample_n":5985},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Anomaly Detection","optional":false},{"name":"Function Calling","optional":false},{"name":"LangChain","optional":false},{"name":"Mastra","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"RAG","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Replit","optional":false},{"name":"Tool Use","optional":false},{"name":"Vercel","optional":false},{"name":"AWS","optional":true},{"name":"Kubernetes","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Terraform","optional":true},{"name":"TypeScript","optional":true},{"name":"Vercel AI SDK","optional":true}],"status":"live","first_seen_at":"2026-03-23T22:19:11Z","employer_posted_date":"2026-03-23","last_verified_at":"2026-09-28T23:46:10Z","board_verified":true,"closed_at":null,"days_open":189,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":188},"description":"What we're building\nIn 2026, we're on the verge of an \"infinite software crisis.\" How will we support, maintain, and operate the explosion in application development?\nOur answer is Sazabi: the AI-native observability platform for fast-moving engineering teams.\nSazabi gives teams a single place to ask questions about their production systems in plain language, automatically visualize what's happening, and get to the root cause 10x faster. No tedious instrumentation. No dashboard configuration. No alert tuning. Just answers.\nWe're backed by tastemakers from the world's top AI companies: Vercel, Graphite, Daytona, Browserbase, LangChain, Mastra, Replit, and more.\nWhat you’ll do\nBuild and iterate on the core AI agents that power Sazabi\n\nDesign systems for anomaly detection, root cause analysis, and automated debugging\n\nWork on prompt engineering, tool use, and agent orchestration\n\nImprove reliability, latency, and correctness of AI-driven workflows\n\nExperiment rapidly with new models, frameworks, and techniques\n\nTranslate messy real-world production issues into structured AI workflows\n\nWhat we're looking for\nStrong experience working with LLMs in production (agents, RAG, tool use, etc.)\n\nDeep curiosity about how and why AI systems fail-and how to fix them\n\nAbility to prototype quickly and iterate based on real-world feedback\n\nStrong engineering fundamentals (this is not just prompt hacking)\n\nComfort operating in a fast-moving, experimental environment\n\nBonus: experience with observability, debugging systems, or developer tools\n\nOur tech\nOur stack is TypeScript end-to-end. We use PostgreSQL for relational data, Temporal for durable execution, and the Vercel AI SDK to orchestrate our AI agents against the latest models. At the infrastructure layer, we use Terraform, Kubernetes, and AWS.\nSome of the most interesting engineering problems we grapple with are:\nAI agents at production scale\n\nLog processing at scale\n\nMulti-region data architecture\n\nReal-time streaming infrastructure\n\nEvals and reinforcement learning\n\nZero-downtime deployments and fast rollbacks\n\nWhat we offer\nCompetitive salary and equity\n\nFree lunches (in-office only)\n\nHealth, dental, and vision insurance\n\nUnlimited paid time off\n\nPaid parental leave\n\nLearn how we think and work\nOur team comes from Brex, Y Combinator, Rootly, Google, Doppel, and other top tech companies. We move fast and hold a high bar for both the product and each other.\nWe operate according to six values:\nIntegrity. We say what we mean, do what we say, and own our mistakes.\n\nUrgency. We treat every week like it matters, because it does.\n\nCraftsmanship. We care deeply about the quality of our work.\n\nService. We're here to make developers’ and our teammates’ lives easier.\n\nKindness. We're direct, and we move fast, but we treat each other well.\n\nFun. We genuinely enjoy working together. If you don't love what you're building and who you’re building it with, what's the point?\n\nYou can find out more about us here:\nWatch our launch video\n\nRead the manifesto\n\nFollow us on X and LinkedIn\n\nThe Sazabi philosophy\nSazabi is more than just a tool. It’s also a philosophy. We're taking a radically different approach to observability, centered on three big ideas:\nLess is more. Most observability platforms drown you in dashboards and modules that you don’t need. We believe observability needs less UI, not more. Sazabi surfaces exactly the information you need in a simple, beautiful chat interface.\n\nLogs are all you need. The “three pillars of observability” idea is outdated. Sazabi accepts only one kind of telemetry: logs. This simplifies the instrumentation and product experience dramatically.\n\nMonitoring is dead. Creating and maintaining static alerts for a fast-evolving system is a fool’s errand. The future is agentic anomaly detection: AI agents that automatically check your app for issues 24-7.\n\nWe came to these beliefs the hard way - after years of building infrastructure and responding to incidents with tools that offered plenty of bells and whistles, but no clear answers when it counted most.\nIf this way of thinking resonates with you, come build with us.","description_format":"text","description_chars":4148,"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":["Equity","Parental leave","Vision insurance"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Observability & APM"],"lifecycle":[{"event":"open","at":"2026-09-12T18:56:39Z"},{"event":"open","at":"2026-09-26T03:22:12Z"}],"liveness":{"score":10,"band":"cold","label":"Long shot","p_open":1,"p_active":0.285,"p_room":0.36,"age_days":188,"expected_fill_days":113,"reasons":["conf:1","win:tail","crowd:"],"computed_at":"2026-09-28T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/sazabi-software-engineer-agents","json_url":"https://alion.io/job/sazabi-software-engineer-agents.json","meta":{"generated_at":"2026-09-29T00:37:22Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":455,"day_limit":5000,"remaining_today":4545,"minute_limit":60,"resets_at":"2026-09-30T00:00:00Z"}}}