LLM Application Engineer (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
LLM Application Engineer (AI): Building LLM-powered applications and agentic workflows for a proactive smart assistant with an accent on reasoning, memory, tool use, and reliable multi-step execution. Focus on designing orchestration systems, evaluating model quality, and translating probabilistic model behavior into predictable, observable, and cost-effective user experiences.
Location: Remote within China; address: Beijing, China.
Company
is building A1, a proactive smart assistant that helps users manage conversations, errands, organization, and everyday workflows.
What you will do
- Build and ship LLM-powered applications and AI agent workflows.
- Design reasoning, planning, memory, tool-calling, and multi-step execution systems.
- Integrate LLMs with APIs, databases, search, internal services, and external tools.
- Develop orchestration pipelines, evaluation frameworks, datasets, and production observability practices.
- Debug and optimize AI systems across models, prompts, backend services, and product UX.
- Collaborate with product and engineering teams to turn ambiguous problems into reliable AI solutions.
Requirements
- Strong software engineering fundamentals and experience building AI-powered applications.
- Hands-on experience with LLMs, generative AI, or agent-based systems.
- Experience designing prompts, workflows, evaluations, or AI behavior.
- Ability to write clean, production-quality Python code.
- Comfort working across model, system, and product abstraction layers.
- Strong problem-solving skills and a bias toward shipping, iteration, and continuous improvement.
Nice to have
- Experience with OpenAI-compatible APIs, open-weight models, agent frameworks, or orchestration systems.
- Experience with vector databases, retrieval systems, backend APIs, distributed systems, PyTorch, or JAX.
Culture & Benefits
- Full-time remote work within China.
- End-to-end ownership of AI problems from user needs through production delivery.
- Focus on measurable user impact, reliability, observability, and continuous improvement.
- Work across product and engineering disciplines in a fast-moving environment.
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 →