Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Site Reliability Engineer (AI/RAG): Designing and operating adaptive retrieval pipelines and agent harnesses for production AI systems with an accent on Agentic RAG, multi-agent architectures, and model-capability-driven engineering. Focus on building benchmark datasets, measuring retrieval and task performance, and using real-world feedback to improve agent intelligence in production.
Location: Asia; work-from-home arrangement, which may vary depending on the business team's work
Company
Binance operates a global blockchain ecosystem offering cryptocurrency trading, finance, payments, institutional services, and Web3 products.
What you will do
- Design and operate adaptive, self-correcting, and multi-hop retrieval pipelines for production AI systems.
- Architect Agentic RAG workflows with dynamic retrieval control, query decomposition, retrieve-reflect-refine loops, and multi-agent collaboration.
- Develop model-capability-driven features including context management, long-term memory, subagents, multi-agent architectures, and real-world task execution.
- Define benchmarks, datasets, annotation strategies, and evaluation methods for retrieval efficiency, latency, groundedness, and task success.
- Use user feedback and real-world task data to run experiments and improve agent and retrieval performance in production.
Requirements
- 2–8+ years of hands-on experience with LLM, RAG, and AI agent systems in production.
- Experience building end-to-end retrieval pipelines with embedding models, vector stores, hybrid search, reranking, chunking, text cleaning, and multimodal data parsing.
- Experience implementing Agentic RAG patterns such as Self-RAG, Corrective RAG, adaptive retrieval, multi-hop decomposition, and retrieve-reflect-refine loops.
- Hands-on experience with agent harness runtimes or equivalent orchestration frameworks, including session recovery, sandbox isolation, middleware, multi-tenant runtimes, plan/execute loops, and retrieval-grounded tool calling.
- Strong knowledge of LLM APIs, KV Cache, agent loops, tool use, reasoning, planning, MCP, memory, subagents, multi-agent systems, prompt engineering, and context engineering.
- Ability to investigate ambiguous problems, conduct independent research, rapidly build prototypes, and use AI-assisted development workflows across unfamiliar technologies.
Culture & Benefits
- Work-from-home arrangement, subject to the nature of the business team's work.
- Autonomous work on fast-paced blockchain and AI-related projects.
- Flat, user-centric organization with collaboration across an international workforce.
- Competitive salary and company benefits.
- Career growth and continuous learning opportunities.
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 →
Похожие вакансии
14 дней назад
AI Engineer
14 дней назад
Principal Site Reliability Engineer (AI)
165 000 - 185 000$
8 дней назад
AI Engineer (AI)
5 часов назад
Senior Site Reliability Engineer (AWS)
P2P.org
10 дней назад
Site Reliability Engineer (Web3)
5 000 - 6 000$
2 дня назад
Site Reliability Engineering Team Lead (Principal SRE, Automotive AI)
132 000 - 211 400$