Portfolio undergoing maintenance. Please email ayush17solanki@gmail.com for queries.
Technical Arsenal
Full-stack ML engineering from research to production
LLM & Generative AI
Large Language Models
Retrieval Augmented Gen
Agentic AI
Prompt Engineering
LLM Framework
Agent Graphs
LlamaIndex
Tool Calling
Agent Memory
Model Context Protocol
Deep Research
LLM Routing
Machine Learning
Machine Learning
Natural Language Proc.
Computer Vision
Deep Learning
TensorFlow
HuggingFace
Model Finetuning
Backend & Systems
Async APIs
Spring Boot
Lightweight APIs
API Design
LLM Gateway
AuthN / AuthZ
Rate Limiting
Caching
Async Workers
Cloud & Infrastructure
Cloud Platform
Cloud Services
Containers
Kubernetes
Observability
Model Deployment
Product & Engineering
Prototyping
AI Products
Automation
Version Control
Model Evaluation
Cost Optimization
Data & Databases
SQL DB
NoSQL
Vector DBs
Query Lang
Data Pipelines
Embeddings
Vector Indexing
Programming Languages
Primary Lang
Systems
Enterprise
Concurrency
ALWAYS AN ACTIVE LEARNER :)
Technical Expertise
Full-stack ML engineering from research to production
AI/ML
Cloud & Infra
Development
Data Systems
Featured Projects
Production systems that drive real business impact
Multi-Agent RAG System
Built enterprise-scale retrieval system with vector embeddings, achieving 40% improvement in retrieval accuracy
Real-time ML Pipeline
Designed distributed training pipeline on AWS with automated model versioning and A/B testing framework
LLM Fine-tuning Platform
Created low-code platform for domain-specific LLM fine-tuning with LoRA and quantization support
Vector Database Optimization
Optimized embedding search reducing query latency by 65% for 100M+ vector database
Let's Build Something Amazing
Open to opportunities in ML Engineering, AI Systems, and GenAI Product Development
Get In Touch→