Performance Engineer - Inference
Zenteiq.Ai · Bengaluru, India
About the role
Improves the performance of systems that serve foundation models by identifying bottlenecks and implementing optimizations.
Skills
- Python
- System Design
- Data Structures & Algorithms
- Distributed Systems
- Transformer Inference
- Accelerator Performance Fundamentals
- Quantization
- Low-Precision Inference
- KV-Cache Optimization
- Speculative Decoding