Software Engineer (Machine Learning - LLMs)
职位介绍
Software Engineer - LLMs focusing on practical, scalable LLM-powered conversational agents.
Hybrid role based in Boston, MA (3 days onsite); collaborate with ML researchers and product teams to ship features.
Own implementation and deployment of LLM-based models and pipelines via REST APIs and internal microservices.
Develop prompt engineering, RAG workflows, tool-use pipelines, and conversation orchestration logic.
Investigate real-time voice, streaming, and multi-modal capabilities; analyze outputs and system performance for iterative improvements.
Build datasets, ensure data quality and reproducibility; partner with ML/backend/product teams on deployment, monitoring, and scalability.
Hybrid role based in Boston, MA (3 days onsite); collaborate with ML researchers and product teams to ship features.
Own implementation and deployment of LLM-based models and pipelines via REST APIs and internal microservices.
Develop prompt engineering, RAG workflows, tool-use pipelines, and conversation orchestration logic.
Investigate real-time voice, streaming, and multi-modal capabilities; analyze outputs and system performance for iterative improvements.
Build datasets, ensure data quality and reproducibility; partner with ML/backend/product teams on deployment, monitoring, and scalability.
查看完整职位
工作职责、任职要求、技能与福利 — 免费创建账号即可查看。
已有账户？ 登录
相似职位
其他可能适合您的职位。