{"id":125099,"url":"https://alion.io/job/yadro-senior-llm-inference-backend-engineer","title":"Senior LLM Inference Backend Engineer","company":{"id":776,"name":"YADRO","domain":"yadro.com","url":"https://alion.io/company/yadro","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"HeadHunter","truth_index":{"grade":"B","score":76,"open_postings":47,"ghost_share":0.277,"stale_share":0,"repost_share":0.489,"time_to_fill_p50_days":23,"computed_at":"2026-10-31T05:58:55Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"senior","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_regions","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Moscow, Russia"],"countries":["RU"],"hiring_countries":["RU","BY","KZ","KG","AM"],"hiring_countries_total":5,"salary":null,"salary_estimate":{"min_usd":33000,"max_usd":68000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":13},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"FastAPI","optional":false},{"name":"Function Calling","optional":false},{"name":"LLM","optional":false},{"name":"Lua","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"OpenAI","optional":false},{"name":"Platform Engineering","optional":false},{"name":"Python","optional":false},{"name":"SGLang","optional":false},{"name":"vLLM","optional":false}],"status":"live","first_seen_at":"2026-10-25T12:26:52Z","employer_posted_date":"2026-10-25","last_verified_at":"2026-10-31T04:13:08Z","board_verified":true,"closed_at":null,"days_open":6,"trust":{"level":"ghost","repost_count":3,"flags":["repost"],"days_open":5},"description":"О команде:\nНаша команда обеспечивает доступность нейросетей для тысяч пользователей одновременно. Мы сопровождаем и улучшаем production-платформу для хостинга LLM: ее надежность, производительность и масштабирование. Кроме того, мы создаём прикладные AI-продукты на базе LLM. Ищем опытного инженера, которому интересно работать и с платформенной частью, и с продуктовой.\n Чем предстоит заниматься:\n Инфраструктура и высоконагруженный инференс (Platform Engineering):\n Проектирование и поддержка GPU-кластера инференса (Nvidia) для десятков тысяч пользователей: скалирование, балансировка и приоритизация запросов, пользовательские лимиты;\n Оптимизация производительности: кэширование, батчинг, etc.;\n Надежность и observability: обеспечение SLA и предотвращение регрессий;\n Оценка и внедрение новых LLM.\n Продуктовая разработка (LLM Application):\n Разработка AI-сервисов: AI Code Assistant (Co-Pilot), AI Chat, AI Code Review;\n Проектирование пайплайнов автоматизаций: tool/function calling, обработка ошибок, управление контекстом/состоянием;\n Интеграции: встраивание AI-сервисов в корпоративную среду (API, БД, legacy-системы).\n Исследования и прототипирование (R&D):\n Проведение экспериментов, создание MVP и выстраивание пути доведения до продакшена;\n Исследование новых технологий и подходов для улучшения продуктов.\n Мы ждем от будущего члена команды:\n Экспертиза в Python & Backend:\n Опыт разработки на Python (5+ лет), знание стандартов: typing, асинхронность, паттерны проектирования;\n Опыт создания высоконагруженных API (FastAPI или аналоги), работа с очередями, воркерами и фоновыми задачами.\n Архитектура и надежность (Production):\n Опыт построения gateway/router, управление ключами, маршрутизация, пользовательские лимиты;\n Опыт поддержки высоконагруженных сервисов в продакшене: стабильность контрактов, обработка ошибок.\n Глубокие знания LLM & Inference:\n Опыт работы с инструментами инференса (vLLM, SGLang, OpenAI API), понимание их внутренней работы;\n Опыт настройки инференса под highload: latency/throughput, управление GPU-ресурсами;\n Опыт построения решений с tool/function calling: MCP, guardrails, борьба с галлюцинациями.\n Дополнительно приветствуем:\n Насмотренность в применении AI агентов, мультиагентных систем, оркестрации инструментов;\n Понимание основных метрик качества LLM решений, опыт проведения A/B-тестов и офлайн-оценки: eval-сеты, human eval, etc;\n Опыт Lua-разработки;\n Опыт разработки и интеграции MCP.","description_format":"text","description_chars":2445,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[{"language":"Russian","level":"Advanced (C1)","optional":false}]},"benefits":[],"hiring_locations":[{"name":"Russia","iso":"RU","kind":"country"},{"name":"Belarus","iso":"BY","kind":"region"},{"name":"Kazakhstan","iso":"KZ","kind":"region"},{"name":"Kyrgyzstan","iso":"KG","kind":"region"},{"name":"Armenia","iso":"AM","kind":"region"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Enterprise Storage Systems","Electronics Manufacturing","Servers & Data Center Hardware","Network Equipment"],"lifecycle":[{"event":"open","at":"2026-08-26T12:26:41Z"},{"event":"reopen","at":"2026-09-15T04:37:06Z"},{"event":"6","at":"2026-09-25T12:26:47Z"},{"event":"6","at":"2026-10-25T12:26:52Z"}],"visa":[],"liveness":{"score":30,"band":"fade","label":"Fading","p_open":1,"p_active":0.3,"p_room":1,"age_days":5,"expected_fill_days":23,"reasons":["conf:1","repost:3","velocity","ghost","win:early"],"computed_at":"2026-10-31T05:58:55Z"},"pay":null,"html_url":"https://alion.io/job/yadro-senior-llm-inference-backend-engineer","json_url":"https://alion.io/job/yadro-senior-llm-inference-backend-engineer.json","meta":{"generated_at":"2026-10-31T22:32:49Z","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":35147,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-01T00:00:00Z"}},"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":776},"rest":"https://alion.io/mcp/rest/get_company?id=776"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fyadro-senior-llm-inference-backend-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%2Fyadro-senior-llm-inference-backend-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%2Fyadro-senior-llm-inference-backend-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/yadro-senior-llm-inference-backend-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fyadro-senior-llm-inference-backend-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":125099}},{"tool":"search_jobs","arguments":{"company":"yadro.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":125099},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}