Senior Deep Learning Scientist, Multimodal Agentic RL

What you'll do

• Develop, train, fine-tune, and deploy large language models for agentic systems, including audio-visual reasoning, tool use, and document understanding.
• Advance multimodal post-training and alignment methods, including instruction tuning, preference optimization, and RLHF/RLVR/MOPD.
• Develop agentic reasoning and grounded perception capabilities; lead multimodal dataset development and benchmarking.

What they ask for

• Master’s degree (or equivalent experience) or PhD in Computer Science, AI, or Applied Math.
• Strong Python programming skills and experience with scalable model development and deep learning frameworks such as PyTorch.
• Knowledge of ML/DL techniques, foundation model architectures including Transformers and mixture-of-experts models, and reinforcement learning fundamentals.
• Hands-on experience post-training multimodal models for audio-visual reasoning, full-duplex voice chat, and human-AI interaction.

Nice to have

• Strong publication record in top-tier AI/ML venues such as NeurIPS, ICML, ICLR, or CVPR.
• Experience with large-scale distributed multimodal model training and deployment, deep RL for agents, audio/speech AI, or embodied AI systems.

Pay

184,000 USD - 287,500 USD (base salary)

Tools

Python, PyTorch, Transformers, mixture-of-experts models, RLHF, RLVR, MOPD

AI focus

Research and develop multimodal agentic AI, including foundation model post-training and alignment, audio-visual reasoning, tool use, planning, and long-horizon task completion.