onsite
AI Researcher - Computer Vision / Multimodal / Generative AI
Research Engineer
Lead cutting‑edge research in photorealistic virtual try‑on and human‑centric visual representation, advancing multimodal vision models from concept to production using Python, PyTorch, and deep learning techniques.
About the role
Key Responsibilities
- Design and implement novel architectures and training strategies for photorealistic virtual try‑on and human‑centric visual representation.
- Advance multimodal learning by integrating vision, language, and video modalities into scalable generative models.
- Translate research prototypes into production‑ready systems, optimizing for realism, controllability, and efficiency.
- Collaborate with cross‑functional teams to define product requirements and evaluate model performance in real‑world scenarios.
- Publish findings in top conferences and maintain a strong research pipeline.
Requirements
- Ph.D. or Master’s in Computer Science, Machine Learning, or related field with a focus on computer vision or generative models.
- Proven experience with deep learning frameworks (PyTorch/TensorFlow) and large‑scale model training.
- Strong background in multimodal learning, vision‑language models, and video understanding.
- Excellent programming skills in Python and ability to write clean, reproducible code.
- Demonstrated ability to move research from prototype to production and communicate results effectively.
Skills
pythonpytorchcomputer visiongenerative aideep learning