Computer Vision Engineer

Job Summary:
We are seeking a skilled Vision Language Model (VLM) Developer to design, train, and optimize multimodal AI systems that integrate computer vision and natural language processing. You will work on cutting-edge projects involving large-scale vision-language models (e.g., CLIP, Flamingo, LLaVA, GPT-4V) to build intelligent applications like image captioning, visual QA, autonomous agents, and AI assistants.
Key Responsibilities:

• Develop, fine-tune, and deploy vision-language models (VLMs) for real-world applications.\
• Work with multimodal datasets, ensuring proper alignment between visual and textual data.
• Optimize model performance for speed, accuracy, and scalability in production environments.
• Experiment with contrastive learning, retrieval-augmented generation (RAG), and instruction tuning for VLMs.
• Collaborate with ML engineers, product teams, and researchers to integrate VLMs into various applications.
• Stay updated with the latest research in multimodal AI, transformers, and diffusion models.
• Implement efficient inference techniques (e.g., quantization, distillation) for edge and cloud deployment. Required Qualifications:
• Strong background in deep learning, computer vision (CV), and NLP.
• Hands-on experience with PyTorch, TensorFlow, or JAX.
• Proficiency in multimodal architectures (e.g., CLIP, BLIP, LLaVA, CoCa).
• Experience with large-scale model training (distributed training, GPU optimization).
• Familiarity with vision transformers (ViT), diffusion models, or LLM fine-tuning.
• Strong programming skills in Python and experience with ML frameworks (Hugging Face, OpenAI APIs).
• Knowledge of datasets like COCO, LAION, or WebVid