AI Engineer | Applied LLM Systems | Backend + RAG Architectures

Building production-focused AI systems that solve real business problems.

AI Engineer with a year of hands-on experience designing and deploying end-to-end AI solutions — from understand business problems to building, integrating, and deploying intelligent systems.

I specialize in combining backend engineering with Large Language Models, retrieval systems, and workflow automation to create scalable, reliable AI applications.

Languages & Core

• Python
• REST APIs
• Event-driven architectures
• Microservices fundamentals

LLM & GenAI

• OpenAI / Gemini / Claude APIs
• Prompt Engineering
• Retrieval-Augmented Generation (RAG)
• AI Agents & Agentic Workflows
• LangChain / LangGraph
• Fine Tuning
• Hugging Face ecosystem
• sentence-transformers
• MLflow
• DVC

Data & Retrieval

• Vector Databases (FAISS, Pinecone, Chroma)
• Relational Databases (Postgres, MySQL, MS-SQL)
• Embeddings & Semantic Search
• NLP Pipelines

Automation & Orchestration

• n8n
• Make
• Workflow automation systems

Deployment & Infra

• FastAPI
• Docker
• Git / GitHub
• Cloud fundamentals (AWS/GCP basics)
• Production integrations & monitoring

• AI chatbots & knowledge copilots
• RAG-based document intelligence systems
• ML-driven automation workflows
• Backend systems integrated with LLM pipelines
• Scalable AI features embedded into existing products
• Business-focused AI tools

• Improving system design fundamentals
• Building scalable and cost-efficient AI pipelines
• Reducing hallucinations through structured retrieval
• Strengthening distributed systems knowledge

• LinkedIn: https://www.linkedin.com/in/anshu-bhadani-255b91216
• Portfolio: https://ai-portfolio-livid.vercel.app/
• Email: a.bhadani0301@gmail.com

⚡ I focus on building reliable, production-ready AI systems that create measurable impact.