AI/ML Learner & Practitioner | System Design Enthusiast
📍 Bengaluru, India • 📧 [email protected] • 🌐 shahbishal.com.np
•
B.E. student in Artificial Intelligence & Machine Learning (2023–2027) with focused expertise in AI engineering, backend development, and scalable system architecture. Passionate about building production-ready machine learning systems and distributed applications. Strong foundation in cloud-native deployments, LLM integrations, and system design principles.
- RAG Systems - Optimized and scalable retrieval-augmented generation architectures
- Fine-Tuning - LoRA, QLoRA, and custom dataset fine-tuning techniques
- OpenAI API Integration - GPT, Whisper, Embeddings, and Assistant APIs
- Gemini API & Embeddings - Google's multimodal AI integration
- LangChain - Building LLM-powered applications and agent systems
- LlamaIndex - Data framework for LLM applications
- LLM Pretraining - Small-scale language model pretraining and optimization
- Vector Databases - Pinecone, Chroma, FAISS implementations
- Model Optimization - Quantization, pruning, and model acceleration techniques
- AI Automation - Agent systems and workflow automation
- ML Deployment - Full-stack deployment using Docker, Kubernetes, REST APIs, and Celery for task queues.
- Distributed Systems - Microservices architecture and design patterns
- API Design - REST/gRPC API implementation and best practices
- Performance Optimization - Load balancing, caching, and CDN strategies
- Database Architecture - Sharding, replication, and optimization patterns
- High Availability - Failover mechanisms and reliability engineering
- Event-Driven Systems - Message queues (Celery) and asynchronous processing
- Scalability Patterns - High-traffic system design and optimization
Professional software, AI, and web development services available through Nytrixx Lab.
"First, solve the problem. Then, write the code." - John Johnson