At Quilter, we are helping electrical engineers save time and accomplish more by automating the tedious and time-consuming task of designing printed circuit boards (PCBs). Our small team is composed of experts in electrical engineering, electromagnetic simulation, ML/AI, and high-performance computing (HPC). We are inventing and leveraging novel techniques to solve the decades-old problem of automating circuit board design where today hundreds of billions of dollars are spent.
Requirements
- Experience with large-scale training of models with 100M+ parameters
- Expertise in distributed training using PyTorch across multi-GPU and multi-node environments
- Knowledge of memory optimization techniques such as gradient checkpointing, mixed precision, and parameter sharding
- Familiarity of training infrastructure including cluster management and job scheduling systems
- Background in model architecture design across transformers, CNNs, and graph networks for geometric data
- Experience with performance optimization focused on training speed, convergence, and scaling laws
- Experience with Reinforcement Learning - combinatorial/constrained optimization problems, sequential decision-making.
Responsibilities
- Develop and train large-scale ML models for PCB layout automation
- Implement efficient and reliable training pipelines for geometric and spatial datasets
- Research and develop novel architectures for circuit board optimization
- Optimize models for both accuracy and low-latency inference
- Collaborate on data pipeline design for PCB and schematic datasets
Other
- Focus on the mission
- Build great things that help humans
- Demonstrate grit
- Never stop learning
- Pursue excellence
