Description

In this role, you will be at the forefront of developing innovative agent systems, scaling reinforcement learning, and collaborating closely with cross-functional teams to transform research into impactful product features.

Requirements

• •Depth in implementing and post-training LLMs/VLMs/Diffusion models
• •Experience modifying and adapting open-source models
• •Strong experience with experimental design
• •Fluency in Python and PyTorch
• •Practical experience building agent loops
• •Hands-on experience with policy optimization
• •Experience with large-scale training
• •Experience with RL for MoE architectures
• •Experience with video and audio modelling
• •Experience with multi-agent settings
• •Strength in alignment and safety evaluations
• •Contributions to open-source, benchmarks, or shared evaluation suites

Tasks

• •Develop agent systems for design, vision, and language tasks
• •Scale post-training and reinforcement learning across distributed systems
• •Contribute to the research agenda for RL and agentic systems
• •Build reward models and learning loops for multi-step reasoning
• •Develop simulation tasks to identify and measure failure modes
• •Establish rigorous evaluation metrics for agents
• •Collaborate with product, design, safety, and platform teams
• •Mentor teammates and present findings to the community

Tools & Technologies

Benefits