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
$109к$149кмедиана$218к
50 в выборке
На СНГ рынке: $4.3к/мес ($3.7к - $5.4к)
87
Крутая вакансия
развернуть
Здесь можно отвечать за конкретные амбициозные AI-функции в продакшене и видеть их эффект, но еженедельные релизы, дежурства и широкая зона ответственности могут означать высокий темп.
?Широкая зона ответственности
Высокий темп
Современный AI-стек
Растущий стартап
AI в ветеринарии
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Product Engineer (AI Team) (AI/veterinary software): Building Jerry, an AI operating system for veterinary practices, with an accent on clinical RAG, real-time transcript classification, voice interaction, and production LLM services. Focus on designing agent workflows, shipping TypeScript and Python features weekly, and operating monitored AI systems used by real clinics.
Location: Hybrid in London, United Kingdom, with work from the London WeWork office most of the week.
Company
hirify.global is building an AI-native operating system for veterinary practices and pet parents, covering scheduling, client communication, clinical documentation, and AI-driven care guidance. The company is a UK market leader and an AI startup with more than 80 employees, $25M in funding, and over 3M pets on the platform.
What you will do
Build Jerry’s clinical guideline library using RAG over vet-approved guidelines, hybrid vector and keyword search in Postgres, and exact-line citations.
Develop listening mode to analyze live consultation transcripts and surface missed charges, tests, or risks in real time.
Build a voice-first mode for ambulatory vets, where changes require vet approval.
Develop long-running and scheduled tasks that continue after the user closes the application and prepare drafts for approval.
Own production delivery across the TypeScript server and Python AI service, including deployment, monitoring, fixes, weekly releases, and on-call participation.
Review AI pull requests and write design documents for new AI features.
Requirements
4+ years of professional software engineering experience, including at least 1 year shipping LLM features to real users in production.
Production experience with TypeScript, Node.js backend development, React, and Python with FastAPI or a similar framework.
Production experience with LLM APIs, including tool calling, agent loops, structured output, and prompt and model iteration.
Experience deploying and owning production code, including CI/CD, Docker, a cloud platform such as AWS, monitoring, and live issue resolution.
SQL and Postgres experience, with fluency in Git workflows including branches, rebasing, pull requests, and code review.
Experience working with AI coding agents such as Claude Code or Codex and critically reviewing their output.
Product-engineering mindset focused on shipping reliable features for real users.
Ability to own work end to end, explain code produced with AI tools, and collaborate directly with vets, product, and engineering.
Nice to have
RAG experience with embeddings, hybrid vector and keyword search using pgvector, reranking, and citations.
Voice AI experience with real-time voice agents, speech-to-text, or telephony integration.
Culture & Benefits
Small team with broad scope and direct collaboration with veterinary, product, and engineering colleagues.
Weekly production releases and direct visibility into the impact on real clinics.
Work is based in the London WeWork office most of the week.
Values include kindness, ambition, pragmatism, end-to-end ownership, and stable monitored production systems.
Success includes contributing to on-call, launching the guideline library, piloting listening mode, and putting scheduled tasks and voice-first functionality into production.
Будьте осторожны
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 →