aipythonllmlangchainci cdobservabilitylanggraphllmopsagentic ai
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
$65к$111кмедиана$142к
20 в выборке
На СНГ рынке: $4.3к/мес ($3.6к - $5.1к)
88
Крутая вакансия
развернуть
Чётко очерченная senior-позиция в AI в продуктовой компании: есть ответственность за production-системы и интересная задача на стыке биомедицины и ИИ. Важное ограничение - гибридный формат в Афинах.
Актуальный стек
Полный цикл разработки
ИИ для биомедицины
?Привязка к Афинам
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior Agent Harness Engineer (AI) (LLMs/Agentic Systems): Design, deploy, and monitor production AI agents for a biomedical knowledge platform with an accent on reliability, evaluation, hallucination prevention, and user-facing research workflows. Focus on selecting models, prompts, tools, and agent architectures, building observability and CI/CD practices, and measuring system performance, latency, and quality.
Location: Athens, Greece; hybrid
Company
hirify.global is building an AI-powered biomedical knowledge platform that uses a high-precision Knowledge Graph and generative AI to help researchers interpret scientific publications, clinical trials, regulatory documents, and other complex data.
What you will do
Design and implement AI agents end-to-end, from ideation through deployment and monitoring.
Apply modularity, testing, code reviews, CI/CD, containerization, and observability to build reliable, maintainable, production-ready AI systems.
Evaluate models, prompts, tools, and agent designs while balancing speed, cost, complexity, interpretability, and performance.
Collaborate with product, design, and engineering teams to define success metrics and incrementally ship AI-powered user-facing features.
Document architectures and decision rationale, and champion model and data quality through evaluation, hallucination checks, and real-world performance tracking.
Mentor junior AI engineers and cross-functional colleagues, share technical knowledge, and track relevant research and tools.
Requirements
Master's degree or higher in Computer Science, Electrical Engineering, or a related field.
5+ years of production software development experience, including LLM-based systems, with ownership of design, evaluation, deployment, and monitoring lifecycle stages.
Proficiency in Python and modern agentic frameworks such as LangGraph or LangChain, including experience integrating LLMs into applications.
Understanding of LLMs and agents, including tool use, context management, prompt engineering, and evaluations.
Strong software engineering foundations in version control, unit and integration testing, CI/CD, containerization, reliability, and scalability.
Experience working in product-focused teams with designers, engineers, and product managers to scope and iteratively ship AI features.
Ability to reason about end-to-end system behavior, including model performance, latency, observability, and user experience impact.
Clear, structured communication skills, including documenting and defending architectural decisions and participating in technical debate.
Nice to have
Experience with LLMOps frameworks and best practices.
PhD in Computer Science, Electrical Engineering, or a related field.
Background or work experience in life sciences, health tech, or other data-intensive domains.
Culture & Benefits
Private medical insurance, enhanced sick leave with five additional days, and 24/7 confidential counselling.
Personal development and individual wellbeing budgets.
Monthly meal vouchers and a day off for your birthday.
Opportunity to contribute to a transformative AI product within an international team.
Equal opportunity employment with consideration for qualified candidates from all backgrounds.
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 →