Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
ЗП не указанаразвернуть
На похожих ролях по рынку
$137к$171кмедиана$205к
28 в выборке
На СНГ рынке: $3.6к/мес ($2.9к - $4.4к)
83
Хорошая вакансия
развернуть
У роли понятный фокус на продакшн-системах с ИИ и современный стек, но высокие ожидания по самостоятельности и формат контрактора оставляют вопросы о нагрузке и трудовых гарантиях.
Высокая нагрузка
?Контрактный формат
Современный стек ИИ
Понятные задачи
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
AI Engineer (TypeScript/LLM): Building and operating production AI systems and LLM workflows with an accent on agentic orchestration, RAG pipelines, prompt engineering, and model routing. Focus on designing reliable tool contracts, evaluating model behavior, debugging hallucinations, and optimizing AI systems for quality, cost, latency, and production stability.
Location: Remote; applicants from any country are welcome if located within approximately ±4 hours of CET. Listed locations include Ukraine, Moldova, Albania, Kazakhstan, Montenegro, the European Union, Serbia, and Georgia.
Company
hirify.global creates and operates consumer products across health, education, and entertainment.
What you will do
Own major AI features and LLM workflows from design through production, including output quality, structure, predictability, and reliability.
Integrate multiple LLM providers through AI gateways, managing model selection, fallback strategies, and cost optimization.
Design agentic and tool-using workflows with function calling, MCP-based tool contracts, and integrations with internal services, search, and background pipelines.
Build and maintain multi-step LLM workflows and RAG pipelines covering indexing, embeddings, retrieval, and re-ranking.
Manage prompt systems, experiments, test datasets, LLM-as-a-judge evaluations, A/B tests, and Langfuse-based tracing.
Develop scalable TypeScript backend logic, tests, monitoring, documentation, and production fixes across Node.js and Cloudflare Workers.
Requirements
4+ years of backend or full-stack software engineering experience, including production-grade TypeScript and Node.js.
1+ year of AI/LLM systems experience in production with real users, not only side projects or experiments.
Daily use of AI-centered development tools such as Claude Code, Cursor, or similar.
Hands-on production experience with LLM APIs such as OpenAI, Anthropic, Google Gemini, or similar, including structured output, function calling, streaming, token control, and cost control.
Experience with agentic AI, multi-step orchestration, tool-based workflows, or RAG pipelines.
Experience with LLM observability and evaluation tools such as Langfuse or LangSmith, and with AI gateways and model routing such as OpenRouter or Cloudflare AI Gateway.
Solid understanding of relational databases, especially PostgreSQL, and caching systems such as Redis or KV.
Exceptional ownership and personal responsibility for engineering quality and delivery.
Nice to have
Evaluation frameworks such as LLM-as-a-judge or RAGAS and experience building test datasets.
MCP server or client development and AI-agent tool-contract design.
Cloudflare Workers, KV, Durable Objects, Queues, R2, or Containers.
OpenSearch, Elasticsearch, pgvector, embeddings, or vector search.
Hatchet, Temporal, Inngest, or other background workflow engines.
Playwright, CDP, browser-use, or browser-agent development.
Fine-tuning for domain-specific tasks or strict JSON/schema compliance.
Working Python for data science, evaluation scripts, or AI tooling.
Culture & Benefits
Remote work with collaboration within approximately ±4 hours of CET.
Unlimited paid time off and paid national holidays.
Company-provided MacBook for employees who need one.
Flexible independent contractor agreement supporting autonomy and remote work.
Fast-paced environment with high ownership, ambitious delivery expectations, and opportunities for professional growth.
Hiring process
Applications are typically reviewed within 3–5 days, though review may take longer due to application volume.
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →