5 дней назад
AI Agent Engineer
Вакансия из Hirify Global, списка международных tech-компанийДля мэтча и отклика нужен Plus
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
AI Agent Engineer (Agentic RAG/LLM): Building production AI agent systems for adaptive retrieval, task execution, memory, and multi-agent coordination with an accent on agent harness engineering, retrieval quality, and real-world evaluation. Focus on designing self-correcting RAG workflows, benchmarking agent intelligence, and rapidly turning research ideas into production prototypes.
Location: Asia; onsite or remote
Company
Binance operates a global blockchain ecosystem spanning cryptocurrency trading, finance, payments, Web3 products, education, and research.
What you will do
- Design and operate adaptive, self-correcting, multi-hop, and multi-agent retrieval pipelines.
- Build agent systems covering context management, long-term memory, subagents, self-evolution, and real-world task execution.
- Develop benchmarks, datasets, annotation strategies, and evaluation methods for retrieval quality and agent intelligence.
- Use user feedback and production task data to improve agent and retrieval performance.
- Collaborate with researchers and engineers to prototype, test, and ship model-capability-driven innovations.
Requirements
- At least 1 year 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, multimodal parsing, and Agentic RAG patterns.
- Experience with agent harness runtimes or equivalent orchestration frameworks, including session recovery, sandbox isolation, middleware, multi-tenant runtimes, and plan/execute loops.
- Strong understanding of LLM APIs, KV cache, tool use, reasoning, planning, memory, subagents, multi-agent systems, MCP, prompt engineering, and context engineering.
- Ability to conduct independent research, generate original ideas, build prototypes, and iterate through experiments quickly.
- Proficiency in AI-assisted development workflows and strong learning velocity across languages, frameworks, and domains.
Nice to have
- Hands-on experience with Claude Code, OpenClaw, Cowork, Manus, Pi Agent, or AgentScope.
- Experience with RAGAS, TruLens, custom RAG evaluation, GraphRAG, or knowledge graphs.
- Background in model training, RLHF, model-system co-design, or LiteLLM.
- Experience with Kubernetes/EKS, sandbox hardening, prompt-injection defense, or guardrail design.
Culture & Benefits
- Work in a global, user-centric organization with a flat structure.
- Handle fast-paced projects with autonomy in an innovative environment.
- Access career growth and continuous learning opportunities.
- Receive a competitive salary and company benefits.
- Work from home may be available depending on the nature of the business team.
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 →