AI Infrastructure Engineer | Competitive Programmer | Full-Stack Developer

🎯 Currently focusing on AI hardware acceleration and cross-platform inference
🔭 Working on OpenVINO XLA plugin for multi-platform model deployment
🌱 Learning hardware-specific optimizations for GPUs, TPUs, and FPGAs
💬 Ask me about ML Infrastructure, Hardware Acceleration, and Competitive Programming

Developing a new plugin for OpenVINO that enables cross-platform model inference:

• 🔄 Converting OpenVINO IR to XLA representation (HLO/MLIR)
• ⚡ Enabling model inference on diverse hardware:
  • NVIDIA GPUs
  • Google TPUs
  • FPGA devices
• 🎯 Supporting various model architectures:
  • Convolutional Neural Networks (CNNs)
  • Transformer-based models
• 🛠️ Tech Stack:
  • OpenVINO Framework
  • XLA (Accelerated Linear Algebra)
  • MLIR (Multi-Level IR)
  • CUDA/GPU Programming

Data Structures & Algorithms

• Arrays & Lists
• Trees & Graphs
• Dynamic Programming

Systems Programming

• OS Fundamentals
• Memory Management
• GPU Architecture

Networks

• TCP/IP
• gRPC
• Load Balancing

Databases

• SQL/NoSQL
• Redis
• Distributed Storage

• 🔥 Model Training: PyTorch, JAX, TensorFlow
• 🌐 Distributed Systems: PyTorch DDP, DeepSpeed, Megatron-LM
• ⚡ Hardware Acceleration: CUDA, cuDNN, NCCL
• 🐳 Orchestration: Kubernetes, Ray, Docker
• 📊 Monitoring: Prometheus, Grafana, OpenTelemetry

• 📐 Advanced Linear Algebra & Tensor Operations
• 🖥️ CUDA Programming & GPU Optimization
• 🔄 Distributed Systems Design
• 🛠️ High-Performance Computing
• 🧮 Competitive Programming