12 months ago
Palo Alto, CA, USAMid Level
Responsibilities
- Post-train frontier models to perform semiconductor design and verification tasks.
- Develop reinforcement learning environments for LLMs and multimodal agents.
- Create reward functions, scaling strategies, evaluation frameworks, datasets, benchmarks, and feedback pipelines.
- Collaborate with hardware design, verification, and computer architecture experts to define evaluation metrics, constraints, and simulation conditions.
- Run large-scale RL fine-tuning and post-training experiments.
- Apply reinforcement learning or curriculum learning to structured reasoning and symbolic domains.
Requirements
- Experience creating and scaling reinforcement learning environments for LLMs or multimodal agents.
- Experience building evaluation datasets and benchmarks for complex reasoning or design tasks.
- Experience working with hardware and verification experts to define metrics, constraints, and simulation conditions.
- Experience designing reward functions and feedback pipelines balancing correctness, performance, and design efficiency.
- Experience running large-scale RL fine-tuning or post-training experiments for frontier models.
- Experience applying reinforcement learning or curriculum learning to structured reasoning or symbolic domains.
Categories
AI ResearchML Engineering
About Voltai
Volt AI builds a real-time video intelligence platform for physical security teams, unifying existing cameras and systems to track people and objects across sites and streamline incident response via an intuitive 3D map and case tools. It sells enterprise software that runs with edge AI and integrates into security workflows. Founded in 2019 and headquartered in Washington, DC, the company is privately held.