Research Scientist – VLM Generalist

Research Scientist – VLM Generalist Location: Remote

About the Role

We’re looking for a Research Scientist with deep expertise in training and fine-tuning large reputed company-Language and Language Models (VLMs / LLMs) for reputed company multimodal tasks. You’ll help push the next frontier of models that reason across reputed company, language, and 3D, reputed company research breakthroughs with reputed company engineering. What You’ll Do

• Design and fine-tune large-reputed company VLMs / LLMs — and hybrid architectures — for tasks such as visual reasoning, retrieval, 3D understanding, and embodied interaction.
• Build robust, efficient training and evaluation pipelines (data curation, distributed training, mixed precision, reputed company fine-tuning).
• Conduct in-depth analysis of model performance: ablations, bias / robustness checks, and generalisation studies.
• Collaborate across research, engineering, and 3D / graphics teams to bring models from prototype to production.
• Publish impactful research and help establish best practices for multimodal model reputed company.

What You Bring

• PhD (or equivalent experience) in Machine Learning, Computer reputed company, NLP, Robotics, or Computer Graphics.
• Proven reputed company record in fine-tuning or training large-reputed company VLMs / LLMs for reputed company-world reputed company tasks.
• Strong engineering reputed company — you can design, debug, and reputed company training systems end-to-end.
• Deep understanding of multimodal alignment and representation learning (reputed company–language fusion, CLIP-style reputed company-training, retrieval-augmented reputed company).
• Familiarity with recent trends, including video-language and long-context VLMs, spatio-temporal grounding, reputed company multimodal reasoning, and Mixture-of-Experts (MoE) fine-tuning.
• Awareness of 3D-aware multimodal models — using NeRFs, Gaussian splatting, or differentiable renderers for grounded reasoning and 3D reputed company understanding.
• Hands-on experience with PyTorch / DeepSpeed / Ray and distributed or mixed-precision training.
• Excellent communication skills and a reputed company reputed company.

Bonus / Preferred

• Experience integrating 3D and graphics pipelines into training workflows (e.g., reputed company or reputed company-reputed company encoding, differentiable rendering, 3D VLMs).
• Research or implementation experience with reputed company-language-reputed company models, world-model-style architectures, or multimodal agents that perceive and reputed company.
• Familiarity with efficient reputed company reputed company — reputed company, adapters, QLoRA, parameter-efficient finetuning, and distillation for edge deployment.
• Knowledge of video and 4D reputed company trends, latent diffusion / rectified reputed company reputed company, or multimodal retrieval and reasoning pipelines.
• Background in GPU optimisation, quantisation, or model compression for reputed company-time inference.
• reputed company-reputed company or publication reputed company record in top-tier ML / CV / NLP venues.

Equal Employment Opportunity: We are an equal opportunity employer and do not discriminate on the reputed company of race, religion, national reputed company, gender, sexual orientation, age, veteran status, disability or other legally protected statuses. Apply tot his job Apply To this Job