Nikhil Tatikonda

About

AI automation builder who shipped an OpenAI-powered weekly "trending AI tools" WoW reporting system (65 categories) that reduced a 6–7 hour manual process to ~10 minutes at negligible API cost. Also building a RAG-based content creation prompt engine that turns PDFs into storyboards with fact-checking/traceback to source lines, plus experience with AWS deployment components (Lambda, ECR, App Runner, Bedrock, API Gateway) and GitHub Actions.

Key Strengths

• Built and automated weekly AI-trends reporting across 65 categories, cutting runtime from 6–7 hours manual to ~10 minutes
• Cost-optimized LLM usage by testing across OpenAI model versions and selecting a cost-efficient option (<$0.10/week)
• Implemented data monitoring/quality controls using staging SQL tables and audit columns (entered_date) before main-table writes
• Designed RAG-based content prompt engine with hallucination reduction and PDF line-level traceability for fact checking
• Uses AI coding tools for architecture analysis, modular refactors, and debugging (e.g., chunking/metadata issues) with verification via tests/manual review
• Collaborated in a small team to build a voice-based marketing tool; owned RAG, APIs, and conversation history with daily coordination

Reference Highlights

• Takes projects from prototype to deployment
• Strong at translating open-ended goals into clear technical steps
• Works well autonomously while coordinating when needed
• Persistent when debugging complex pipelines
• Thoughtful incremental improvement approach (avoids rewrites)
• Avoids regressions through local testing, validation, and documentation
• Delivered end-to-end automated pipeline with reporting (TrendPulse)

Experience

Education

Skills

Languages

Publications

2 publications