AI Engineer
Summary
Build AI-driven GPU optimization pipelines using reinforcement learning and automated code generation to improve performance for large-scale AI workloads and edge devices.
We are looking for an AI Engineer to help build the next generation of AI-for-GPU optimization pipelines, with a focus on automated optimization, AI infrastructure, and edge performance.
Key Responsibilities
Automated Optimization Pipeline
- Develop and optimize an agentic pipeline for GPU performance tuning.
- Apply techniques such as syntax-guided synthesis, reinforcement learning, and automated code generation to improve GPU performance.
AI Infrastructure
- Integrate performance-critical GPU components into high-throughput inference engines
- Optimize latency and performance for Mixture-of-Experts (MoE) architectures and dynamic AI workloads.
Edge AI Performance
- Contribute to continuous pre-training, structural pruning, and architecture optimization for Small Language Models (SLMs).
- Develop efficient AI solutions for hardware-constrained edge environments.
Requirements
- Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or a related discipline.
- 5 years of relevant experience in GPU optimization
- Relevant experience in AI/ML engineering
- Knowledge of GPU programming, performance optimization, and AI inference systems.
- Strong analytical and problem-solving skills
EA Reg No.: R1106634
License No. 22C1076
