10 часов назад
Senior AI Engineer (LLM Agents)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Senior AI Engineer (LLM Agents): Designing and productionizing LLM-powered agents, MCP tools, memory systems, and evaluation frameworks for materials science search, Q&A, and information extraction with an accent on multi-step reasoning, tool orchestration, and measurable answer quality. Focus on building reliable production AI services, instrumenting observability, and developing retrieval and evaluation systems that outperform general-purpose AI.
Location: Singapore; on-site
Company
's Materials team builds AI systems for searching, extracting, and reasoning over materials science and patent data.
What you will do
- Design, build, and productionize agentic systems for materials science search, Q&A, and information extraction.
- Develop and maintain memory systems, MCP servers, agent skills, and multi-agent workflows.
- Build evaluation frameworks with materials domain experts to measure answer quality, extraction accuracy, and retrieval performance.
- Own production reliability, monitoring, and observability for developed AI agents.
- Advise adjacent teams on agentic and search system design and assess technical risks and feasibility during roadmap planning.
Requirements
- Degree in engineering, computer science, or a quantitative or physical science, or equivalent practical experience.
- 5+ years of software or ML engineering experience, including 2+ years building production LLM-based systems.
- Experience designing LLM or agent evaluations, including evaluation sets, quality metrics, and human-expert or LLM-judge pipelines.
- Experience instrumenting, monitoring, and debugging live AI services.
- Strong Python skills and the ability to independently build and deploy services.
Nice to have
- Search and RAG experience with vector databases, keyword search, knowledge graphs, reranking, or hybrid retrieval.
- MCP or agent-tool ecosystem experience.
- Materials science, chemistry, or patent and IP domain exposure.
- Experience with structured information extraction from technical documents.
Culture & Benefits
- Full ownership of a production agent stack used by paying customers.
- Evaluation results directly inform the product roadmap.
- Work in a small senior team with direct access to domain experts and real R&D users.
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 →