ByteDance currently has 112 active AI-related job listings. The majority of these roles are focused on serving infrastructure, accounting for 39% of the total, followed by agents at 27%. Engineering is the most frequent function, with research also being a significant area. The company is hiring for these positions primarily in the United States. Frequent tech tags include model_serving, inference_infra, and multimodal. In the last 30 days, ByteDance added 14 new AI roles, representing a 27% increase compared to the previous 30-day period.
ByteDance currently has 115 active AI-related roles in our index. The most common open titles are: Cloud Acceleration Engineer – DPU & AI Infra (2), LLM AIOps Development Engineer - Data Center Networking (2), Multimodal Model Training and Inference Optimization Engineer (2), Research Engineer - LLM Training Infrastructure - Seed Infra (2), Research Engineer - LLM/VLM Inference Optimization (Seed Infra) (2). Most positions are in Engineering and Research.
ByteDance's active AI hiring is concentrated in: serving infrastructure (38%), agents (25%), post-training (12%). These categories follow a seven-stage AI lifecycle: data, pre-training, post-training, serving infrastructure, agents, evaluation, and application.
ByteDance is hiring AI talent in: United States (115 roles).
Job postings at ByteDance most frequently mention: Machine Learning, Production ML Systems, Algorithms & Data Structures, GPU Computing, Optimization Methods.
In the past 30 days, ByteDance has posted 2 new AI-related roles. That is a -78% change versus the prior 30 days (9 → 2).
Currently tracking 109 active AI roles, down 43% versus the prior 4 weeks. Primary focus: Serve · Engineering.
| Title | Stage | AI score |
|---|---|---|
| Research Scientist - Seed Responsible AI Research Scientist focused on Responsible AI, researching core mechanisms of AI foundation models and agents to ensure reliability, safety, and trustworthiness, with contributions to product development in AI safety and ethics. | Post-trainAgent | 9 |
| Research Scientist, HCI-Multimodality - Interaction Perception, PICO Research Scientist focused on developing computer vision, NLP, and LLM algorithms for next-generation VR intelligent interaction, including input methods, prediction, error correction, and multimodal fusion. The role involves delivering technical innovations, patents, and research translation, with a focus on lightweight models for VR/edge devices. | Post-trainAgent |
| 9 |
| Research Engineer/Scientist (all levels), Efficient Models Research Engineer/Scientist focused on developing efficient algorithms and architectures for large-scale generative and multimodal models, with an emphasis on model distillation, compression, and hardware-efficient inference for applications like image generation, video generation, and VLMs. | Post-trainServe | 9 |
| Sr. Research Engineer/Scientist (all levels), Efficient Models Research Engineer/Scientist focused on applied research in Generative AI and CV/Multimodal Understanding, specifically on designing and implementing efficient models for large-scale generative AI through techniques like distillation and compression. The role involves developing methods and infrastructure for transferring capabilities from foundation models into smaller, more efficient models for scalable training, optimization, and deployment, with applications in image generation, video generation, and VLM. | Post-trainServe | 9 |
| Sr. Research Engineer/Scientist (all levels), Efficient Models Research Engineer/Scientist focused on applied research in Generative AI and CV/Multimodal Understanding, specifically on designing and implementing efficient models for large-scale generative AI through techniques like distillation and compression. The role involves developing methods and infrastructure for transferring capabilities from foundation models into smaller, more efficient models, enabling scalable training, optimization, and deployment, with applications in image generation, video generation, and VLMs. | Post-trainServe | 9 |
| Research Scientist in Large Multimodal Models Applications - San Jose Research Scientist role focusing on applying large multimodal models to multimedia applications like video understanding, processing, and compression. Involves model training, tuning, and performance optimization, with a strong emphasis on academic research and publication. | Post-trainServe | 9 |
| Research Scientist, Applied GAI-Vision Research Scientist role focused on applied research in Generative AI and Computer Vision/Multimodal Understanding, with the goal of delivering intelligent solutions to ByteDance products. The role involves conducting cutting-edge research, transferring advanced technologies, and exploring new AI-centric products, with a focus on generative models for content creation, image/video synthesis, editing, and virtual humans. | Post-trainServe | 9 |
| Research Scientist, Intelligent Editing (Multimodality) Research Scientist role focusing on multimodal understanding, vision and language, large-scale training, and RLHF for intelligent editing within ByteDance's Intelligent Creation Team. The role involves cutting-edge research and transferring technologies to products. | Post-trainPretrain | 9 |
| 3D Avatar Research and Development - PICO Perception - San Jose Research and development role focusing on 3D Avatar generative models, involving 3D geometry, texturing, human reconstruction, and animation techniques. Requires expertise in generative modeling for 3D/4D reconstruction/generation, with a Master's degree or above and proficiency in deep learning frameworks. | Post-train | 8 |
| Vision Scientist - PICO Lab - San Jose Research role focused on developing AI imaging algorithms and perceptual metrics for AR/VR products, applying perception sciences, and designing eye-tracking features. Requires advanced degree, 5+ years experience, strong background in statistics, optimization, machine learning, and computational modeling, with experience in psychophysics and user studies. | Post-train | 7 |