🔹 Lead Data Scientist with expertise in LLMs, RAG, Vector Databases, and Cloud AI
🔹 Passionate about optimizing AI for performance, cost-efficiency, and scalability
🔹 Contributor to Open-Source AI Projects & DevOps Automation
🔹 Experienced in FastAPI, LangChain, Pinecone, Weaviate, Docker, AWS Lambda, Kubernetes
🔹 Exploring Multi-Cloud AI Deployments & Enterprise-Grade LLM Systems
🖥️ Portfolio: qaicodes.com
🔗 LinkedIn: linkedin.com/in/qurratulain
✍ Medium: medium.com/@qaicodes
💻 GitHub: github.com/qaicodes
🔗 GitHub | 🖥️ Live Demo
📌 Tech Stack: Python, FastAPI, OpenAI API, LangChain, FAISS, Pinecone, Weaviate
📌 Highlights:
✅ Reduced response time from 2s → 400ms via optimized vector retrieval
✅ Hybrid search (BM25 + dense embeddings) for improved search relevance
✅ Deployed on AWS Lambda with API Gateway for serverless scalability
🔗 GitHub | 📖 Blog Post
📌 Tech Stack: GraphDB, Neo4j, LangChain, Weaviate, OpenAI, FastAPI
📌 Highlights:
✅ Enhanced RAG workflows using graph-based contextual retrieval
✅ Optimized LLM context window usage, reducing token costs by 40%
✅ GraphQL-powered API for fast & flexible knowledge retrieval
🚀 Reduced AI model latency from 2s → 400ms in production RAG pipelines
🚀 Optimized retrieval workflows, improving search accuracy by 40%
🚀 Lowered AI deployment costs by 35% via serverless cloud architecture
🚀 Built multi-modal AI systems integrating NLP, OCR, and RAG pipelines
🚀 Contributed to vector search optimizations for open-source LangChain modules
🔹 LangChain – Developed custom retriever & function calling modules
🔹 Weaviate & Pinecone – Fine-tuned hybrid search performance & cost efficiency
🔹 FastAPI – Created high-performance ML serving APIs
🔹 Neo4j GraphDB – Integrated knowledge graphs into RAG pipelines
🔹 AWS Lambda AI Deployments – Optimized serverless inference scaling
📖 Designing Large-Scale AI Systems – Chip Huyen
📖 Deep Learning for LLMs – Andrej Karpathy’s Lecture Series
📖 Retrieval-Augmented Generation for AI Applications – DataCamp
📖 MLOps & Scalable AI Deployment – DeepLearning.AI
🚀 Open to remote AI engineering roles & collaborations!