4 дня назад
Principal AI Agent Development Engineer/Architect (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Principal AI Agent Development Engineer/Architect (AI Agents): Building production-grade agent platforms, orchestration runtimes, MCP integrations, and lifecycle toolchains for a global cryptocurrency exchange with an accent on steerable agent loops, multi-agent collaboration, and measurable effectiveness. Focus on designing 0-to-1 agent systems, optimizing token cost and latency, implementing evaluation and monitoring loops, and protecting financial workflows from prompt injection and compliance risks.
Location: Kuala Lumpur, Malaysia
Company
is a cryptocurrency exchange and digital financial platform providing trading, payments, wealth management, custody, institutional services, and Web3 products.
What you will do
- Design and implement the agent SDK, orchestration engine, runtime, and core primitives.
- Build steerable, verifiable, conversational, and adaptive agentic loops.
- Expand the MCP matrix by integrating internal systems as MCP servers, sub-agents, and agent skills.
- Unify tool discovery, dynamic registration, RBAC, rate limiting, and version management.
- Build agent development lifecycle tooling covering specification, evaluation, testing, A/B experiments, canary releases, monitoring, and iteration.
- Own agent accuracy, resolution rate, cost, latency, and personalization optimization through data feedback loops.
Requirements
- Bachelor’s degree or higher in Computer Science, Software Engineering, or a related field.
- 6+ years of experience, including 3+ years in AI or agent engineering; P7+ candidates should have 8+ years of experience and 0-to-1 agent platform experience.
- Production-grade proficiency in Go or Python, system design, and TRD documentation.
- Deep expertise in LLM APIs, prompt engineering, ReAct patterns, and context window management.
- Experience launching and continuously iterating a production agent system, beyond demo or POC work.
- Hands-on experience with an orchestration framework, multi-agent collaboration, and either RAG engineering or evaluation systems.
Nice to have
- Experience building agent simulation or benchmarking platforms.
- Private LLM deployment experience with vLLM, Triton, DeepSeek, Qwen, or GLM.
- Domain expertise in crypto AI, AIOps, customer service AI, or code AI.
- AI security research or open-source contributions to agent frameworks and MCP projects.
- Public technical influence through blog posts, conference talks, papers, or open-source projects.
Culture & Benefits
- Professional development support through a Study Growth Fund.
- Internal team-building activities, workshops, and collaboration events.
- Collaboration with an international team across multiple regions.
- Career advancement opportunities in a rapidly expanding digital asset company.
- Internal mobility opportunities for long-term career development.
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 →