{"id":727655,"url":"https://alion.io/job/telli-engineering-voice-ai","title":"Engineering, Voice AI","company":{"id":63384,"name":"Telli","domain":"telli.com","url":"https://alion.io/company/telli","size_band":"201-500","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":83,"open_postings":6,"ghost_share":0,"stale_share":0.667,"repost_share":0,"time_to_fill_p50_days":39,"computed_at":"2026-10-01T05:45:00Z"}},"role":"AI/ML","role_family":"AI/ML","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":["Berlin, Germany"],"countries":["DE"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":85000,"max":160000,"currency":"EUR","period":"year","gross":null,"usd_annual":183673},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":true,"technologies":[{"name":"AI Agents","optional":false},{"name":"ChatGPT","optional":false},{"name":"Claude","optional":false},{"name":"RAG","optional":false},{"name":"Slack","optional":false},{"name":"SQLite","optional":false},{"name":"Voice Agents","optional":false},{"name":"WhatsApp","optional":false},{"name":"AWS","optional":true},{"name":"Azure","optional":true},{"name":"Cloudflare","optional":true},{"name":"FastAPI","optional":true},{"name":"Fastify","optional":true},{"name":"GCP","optional":true},{"name":"Honeycomb","optional":true},{"name":"JavaScript","optional":true},{"name":"LiveKit","optional":true},{"name":"Node JS","optional":true},{"name":"OpenTelemetry","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Python","optional":true},{"name":"React.js","optional":true},{"name":"Redis","optional":true},{"name":"TypeScript","optional":true},{"name":"Vite","optional":true}],"status":"live","first_seen_at":"2026-05-28T17:05:12Z","employer_posted_date":"2026-05-28","last_verified_at":"2026-10-01T02:14:38Z","board_verified":true,"closed_at":null,"days_open":125,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":125},"description":"about us\nEvery 10 minutes, 18 million conversations happen between businesses and consumers around the world.\nFor decades, the consumer side of those conversations sucked: long queues, robotic menus, repeated explanations, and advice that is often unhelpful. Most people today still cannot simply say what their problem is in natural language when communicating with businesses.\nAI changes that. For the first time, companies can have natural conversations with customers at massive scale. Every B2C company - from energy providers to telcos to insurers - will use AI agents to talk to their customers. The number of conversations businesses will handle is going to explode in the coming years.\nAt telli, we are solving the challenges that come with that shift. Today, leading B2C companies like Sky are already using telli to deploy thousands of voice agents to provide their customers with a new experience. But building a first voice agent is easy, getting it to drive real outcomes for customers and businesses is the hard part. telli helps companies build, deploy, and improve consumer-facing AI voice agents at scale. This will become one of the most important software categories of the next decade, and we intend to win it.\nWe are a small, AI-pilled team that likes to solve hard problems. Be it engineering, product, or GTM - we build, experiment, and move fast, while heavily leveraging the capabilities of AI models. All of us like to challenge ourselves and take real ownership over what we do, all while still staying humble and keeping a low-ego culture.\nCheck out our principles to see how we work.\nabout the role\nThis role is for engineers who care about velocity and solving real customer problems. You won't just ship code; you will own projects end-to-end, make core product and technical decisions, and shape the trajectory of this company.\nOur philosophy is to push the frontier models to the limits of what is possible - and to achieve that, we need your help.\nWe are a small team working across:\nharness engineering\n\napplied AI products\n\nrealtime audio\n\ndistributed systems\n\nwhat you will work on\nVoice AI\nVoice AI is one of the hardest technical challenges we have right now. We need to ensure that the voice AI we deliver is fast, reliable, and high-quality.\nTopics that we are currently working on:\nNo-infra RAG using SQLite artifacts downloaded for each call.\n\nRacing LLMs to use the fastest one at any given moment.\n\nShadow-test new transcribers on real calls before switching production traffic.\n\nMake Voice agents respond faster without reducing quality.\n\nMake every bad call easy to understand and debug.\n\nMulti-channel agents\nCurrently, our agents are primarily voice agents, but we will extend their capabilities to be able to handle any channel.\nBuild an agent that is able to call someone, follow up on WhatsApp, wait three days for a reply, send an email, and continue exactly where it stopped.\n\nLet agents choose the right channel instead of forcing every interaction into a phone call.\n\nShare memory, tools, and state across realtime and asynchronous conversations.\n\nCall scheduler\nWe have to develop a distributed call scheduler that will manage load across our voice orchestration. It has to handle many race conditions and distribute the load evenly across customers while applying additional rules.\nStart large call batches without letting one customer consume all available capacity.\n\nPrevent duplicate calls even when workers crash, restart, or race each other.\n\nHandle time zones, calling windows, retries, provider limits, and changing capacity.\n\nKeep the system moving when individual calls, workers, or providers fail.\n\nAgent memory\nOur agents have multiple interactions with customers, so we need to ensure they can reason throughout the whole flow.\nTopics we have to develop:\nWhat information should be persisted in memory?\n\nHow should the voice agent access memory?\n\nShould agents share memory?\n\nCharlie\nCharlie is our AI coworker for building, configuring, debugging, and improving agents.\nEnable Charlie to use every capability in our product without building one-off tools.\n\nMake Charlie available through the app, Slack, Teams, ChatGPT, and Claude.\n\nMake every action token-efficient, traceable, and easy to understand.\n\nEnable Charlie to use customer-context to make effective proactive suggestion on improving agents\n\nAnalytics & Dashboard\nWe want Charlie to replace dashboards full of charts with direct, useful answers.\nEnable Charlie to turn plain-language goals into business KPIs.\n\nGive Charlie the context to explain metric changes and trace them to exact calls.\n\nEnable Charlie to surface trends, regressions, and opportunities automatically.\n\nWorkflows\nVoice agents need to do real work, not just have conversations.\nEnable Charlie to connect agents to CRMs, calendars, WhatsApp, email, and customer systems.\n\nGive Charlie the ability to build workflows that wait, retry, and resume.\n\nEnable Charlie to inspect failures, explain their cause, and suggest a fix.\n\nwhat we look for\nWe believe that today, engineers must not only know how to ship code but also ensure they work on the right problems. These are the core skills we look for in the interview process:\nYou have built and owned distributed systems in production.\n\nYou have strong software fundamentals and learn unfamiliar domains quickly.\n\nYou are eager to act, biased towards action, and want to get your hands dirty.\n\nYou want to figure things out on your own rather than waiting for people to tell you what to do.\n\nYou don’t take what people say as given; you want to understand the problems yourself and challenge the status quo.\n\nYou are excited about agentic coding, but can do it with awareness ensuring quality\n\nYou are a team player: You optimize for the engineering organization’s output, not your individual output.\n\nour tech stack\nVoice and backend: Python, uv, FastAPI, LiveKit, TypeScript, Bun, Node.js, Fastify\n\nFrontend: React, Vite, TanStack\n\nData and workflows: PostgreSQL, Redis, Temporal, SQLite\n\nObservability: OpenTelemetry, Honeycomb, Better Stack\n\nInfrastructure: AWS, GCP, Azure, Cloudflare, Render, Cerebrium, Modal\n\nwhat may not make you a good fit\nyou prefer a remote-first environment\n\nyou want to be told exactly what to do\n\nyou mostly care about the tech, not business outcomes\n\nyou want to work 9-5\n\nperks\nvery competitive pay + equity package\n\naccess to any (AI) tools\n\nlarge token budget\n\nfree dinners if you stay late\n\nurban sports\n\nrelocation support if you don’t live in Berlin","description_format":"text","description_chars":6538,"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"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":true,"industries":["Conversational AI","Lead Generation","Marketing & Sales AI"],"lifecycle":[{"event":"open","at":"2026-09-11T08:56:30Z"}],"liveness":{"score":10,"band":"cold","label":"Long shot","p_open":1,"p_active":0.371,"p_room":0.28,"age_days":125,"expected_fill_days":39,"reasons":["conf:3","win:tail","crowd:"],"computed_at":"2026-10-01T05:45:00Z"},"pay":{"stated_usd_annual":183673,"is_top_pay":false},"html_url":"https://alion.io/job/telli-engineering-voice-ai","json_url":"https://alion.io/job/telli-engineering-voice-ai.json","meta":{"generated_at":"2026-10-01T12:18:49Z","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":3641,"day_limit":5000,"remaining_today":1359,"minute_limit":60,"resets_at":"2026-10-02T00:00:00Z"}}}