LLM and Multimodal Post-training-AliStar Expand

Alibaba Group; Sunnyvale (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Alibaba Group in Sunnyvale, CA is seeking outstanding research scientists and engineers for the next generation of LLM and Multimodal Agent systems. You will advance post-training methods and agent capabilities to enable complex tasks such as DeepResearch, tool use, coding, and long-horizon reasoning.

You will collaborate with leading researchers and engineers, design training approaches like Agentic SFT and CPT, build large-scale datasets, and contribute to open-source projects or publications

Qualifications

• Master’s or PhD in CS/AI or related field.
• Experience with LLM training or post-training (fine-tuning).
• Publications in NeurIPS, ICML, ICLR or CVPR, or significant open-source contributions.

Responsibilities

• Research and develop post-training methods for LLM and multimodal models.
• Design and implement training approaches such as Agentic SFT, Agentic CPT, Reasoning RL, and Agentic RL.
• Build large-scale agent training datasets for complex tasks like DeepResearch, tool use, and coding.
• Design and implement agent evaluation frameworks for complex task execution and tool-use scenarios.
• Collaborate with model training, data engineering, and systems teams to translate research into real-world AI systems and products.
• Contribute to the AI community through open-source projects or publications.

Skills

LLM training

Multimodal systems

Deep research

Education

Master’s or PhD in CS/AI

Job description

LLM and Multimodal Post-training-AliStar

Updated on 2026-07-30

Sunnyvale

Basic Information

Graduation Dates 2026-11-01 - 2027-10-31

Job Category Technology

Hiring Program Alibaba 2027 Graduate Recruitment

About the Job

We are looking for outstanding research scientists and engineers to advance the next generation of LLM and Multimodal Agent systems.

This role focuses on frontier research in large model post-training and agent capability training, aiming to enable foundation models to perform complex tasks such as DeepResearch, tool use, coding, and long-horizon reasoning. You will work closely with a team of leading researchers and engineers to explore and develop next-generation post-training approaches, including Agentic SFT, Agentic CPT, Reasoning RL, Agentic RL, and RLHF, pushing the boundaries of AI systems in complex real-world tasks.

1. 1、Conduct research and develop post-training methods for LLM and multimodal models, with a focus on improving agent capabilities and complex reasoning.
2. 2、Design and implement training approaches such as Agentic SFT, Agentic CPT, Reasoning RL, and Agentic RL.
3. 3、Build large-scale agent training datasets covering complex tasks such as DeepResearch, tool use, and coding.
4. 4、Design and implement agent evaluation frameworks to measure model performance in complex task execution and tool-use scenarios.
5. 5、Collaborate with teams across model training, data engineering, and systems to translate research advances into real-world AI systems and products.
6. 6、Contribute to the broader AI community through technical sharing, open-source projects, or academic publications.

Qualifications

1. 1、Master’s or PhD degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field.
2. 2、Experience with LLM training or post-training (fine-tuning / post-training).
3. 3、Publications in top-tier conferences such as NeurIPS, ICML, ICLR, or CVPR, or significant contributions to open-source projects.

Hiring Business

Alibaba International Digital Commerce Group