{"id":546384,"url":"https://alion.io/job/vahan-lead-ai-engineer","title":"Lead AI Engineer","company":{"id":15903,"name":"Vahan","domain":"vahan.co","url":"https://alion.io/company/vahan","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Work at a Startup","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"lead","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":3000000,"max":6000000,"currency":"INR","period":"year","gross":null,"usd_annual":63414},"salary_estimate":null,"experience_years_min":6,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Claude Code","optional":false},{"name":"Fine-tuning","optional":false},{"name":"LLM","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Speech Recognition","optional":false},{"name":"WhatsApp","optional":false},{"name":"ClickHouse","optional":true},{"name":"Deepgram","optional":true},{"name":"ElevenLabs","optional":true},{"name":"Knowledge Distillation","optional":true},{"name":"LiveKit","optional":true},{"name":"Model Context Protocol","optional":true},{"name":"Model Distillation","optional":true},{"name":"NLP","optional":true},{"name":"SQL","optional":true}],"status":"live","first_seen_at":"2026-09-08T12:42:18Z","employer_posted_date":"2026-10-21","last_verified_at":"2026-10-25T22:12:42Z","board_verified":true,"closed_at":null,"days_open":47,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":47},"description":"Role title: AI Engineer III\nLocation: Bengaluru (On-site)\nExperience: 5+ years\nAbout Vahan\nVahan is a marketplace for blue-collar work. Zomato, Zepto, Swiggy and others hire through us; hundreds of recruitment agencies source through us. Samvaadini, our hybrid voice and WhatsApp agent, places 100,000+ outbound calls a day to people looking for delivery and warehouse work across 900+ Indian cities - qualifying them, answering questions about pay and shift timings, and handing the serious ones to a recruiter. It speaks Hindi, Hinglish, and a widening set of regional languages, mostly to people on low-end Android phones in noisy streets, many of whom have never used a chatbot before. When Samvaadini gets better, more people get placed in a job this week instead of next month.\nThe Role\nYou'll own outcomes across the system, not one component - the voice and WhatsApp agents, the eval suite, the conversion funnel they feed, and root-cause analysis across code, agent behaviour, models, and data. At this level you'll more often be handed a number that moved than a task to complete: qualified handoffs down 12%? You localize it across code, agent behaviour, a silent model change, upstream data, or a market shift, then argue for the fix with the most leverage.\nWhat You'll Do\nOwn the outcome, not the ticket - investigate metric moves end to end and argue for the highest-leverage fix (sometimes that's doing nothing)\nKnow the funnel cold: outreach, connect, qualify, handoff, interview, placement - write your own queries\nOwn agent behaviour end to end: the loop, tool surface, context management, stop conditions, retries, and timeout handling\nBuild and defend the eval suite - every behaviour change ships behind a golden set and a regression gate\nFight for latency and cost - time-to-first-audio and inference cost at 100K calls/day are yours to defend\nWork the voice pipeline - streaming ASR on code-switched Hinglish, turn detection, barge-in, graceful failure on network drops\nDebug production non-determinism - reproduce rare failures, write postmortems, close the loop with evals\nUse coding agents hard and well - Claude Code from Day 1\nWhat We're Looking For\nShipped an LLM-backed system in production, with real users, long enough for it to break\nCan trace a business metric to its root cause across any layer - as comfortable in a warehouse query as a stack trace\nStrong async Python - you write services, not notebooks\nBrings up evaluation before we do\nModel-choice opinions grounded in latency and cost - and you change them when shown better numbers\nFluent with coding agents; can name the last time one confidently produced something wrong and how you caught it\nCan explain a technical trade-off to a recruiter or ops lead without dumbing it down\nLearns fast in public\nNice to Have (Genuinely Not Required)\nReal-time voice stacks (LiveKit, Pipecat, Deepgram, ElevenLabs, Cartesia, telephony); Hindi/Hinglish or code-switched NLP; fine-tuning/distillation; durable workflow orchestration; ClickHouse or comparable analytical SQL; open-source work or public writing; MCP server authoring.","description_format":"text","description_chars":3111,"description_truncated":false,"requirements":{"experience_years_min":6,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[{"language":"Hindi","level":"All levels","optional":false}]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Recruiting & Staffing","HR & Recruiting AI"],"lifecycle":[{"event":"open","at":"2026-09-08T12:42:18Z"}],"visa":[],"liveness":{"score":24,"band":"cold","label":"Long shot","p_open":1,"p_active":0.536,"p_room":0.45,"age_days":46,"expected_fill_days":30,"reasons":["conf:2","win:tail"],"computed_at":"2026-10-25T05:49:26Z"},"pay":{"stated_usd_annual":63414,"is_top_pay":false},"html_url":"https://alion.io/job/vahan-lead-ai-engineer","json_url":"https://alion.io/job/vahan-lead-ai-engineer.json","meta":{"generated_at":"2026-10-25T22:27:27Z","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":31724,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-26T00:00:00Z"}},"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":15903},"rest":"https://alion.io/mcp/rest/get_company?id=15903"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fvahan-lead-ai-engineer"},{"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%2Fvahan-lead-ai-engineer"},{"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%2Fvahan-lead-ai-engineer"},{"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/vahan-lead-ai-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fvahan-lead-ai-engineer"}]}