DAVID MAMANI RESEARCH · AI ENGINEER / DATA ENGINEER

Drag to rotate the sculpture. Use the arrow keys to rotate, Space to nudge it, and R to reset its orientation.

RL for Infrastructure Optimization

Applying RL to auto-scaling decisions in cloud-native AI deployments

ML ENGINEERINGDATA ENGINEERING

Investigating how deep reinforcement learning agents can make proactive auto-scaling decisions for GPU-intensive inference workloads, reducing both cost and latency.

Hypothesis
RL agents outperform threshold-based autoscalers for GPU workloads
Reinforcement Learning · Cloud
Methodology
PPO agent trained on 6 months of production traffic data
Stable Baselines3 · GCP · Prometheus
Findings
40% cost reduction with 15% lower p99 latency
Deployed in staging environment

Visit GitHub Profile ↗

Local time (UTC-5:00)

AI Engineer and 3x Hackathon winner specializing in agentic AI orchestration and data engineering. AWS Certified Data Engineer focused on physics, calculus, and statistics. Currently completing a B.S. in Civil Engineering.

-- × -- -- fps

AREQUIPA, PERU

AI ENGINEER / DATA ENGINEER