Sai Kumar Reddy
AI/ML Engineer | Generative AI | LLMs | RAG | MLOps
This profile was put together from Sai's public GitHub portfolio, and they haven't joined Vibetown yet, so reach them through their portfolio. Is this you? Contact us to update or remove it.
About
Sai Kumar Reddy works in AI engineering and ML & data science, based in Dallas, TX (Teledyne Technologies Incorporated). AI/ML Engineer | Generative AI | LLMs | RAG | MLOps. Public projects on GitHub include Llm Eval Observability (Evaluation, judge calibration, tracing and a CI regrssion gate for RAG systems, run against…), Voice Ai (Full-duplex voice agent with measured barge-in) and Ai Doctor (Document intelligence and grounded RAG platform over PDF, DOCX, PPTX, XLSX, HTML and Markdown), mostly written in Python.
Projects 6
- github.com
Llm Eval Observability
Evaluation, judge calibration, tracing and a CI regrssion gate for RAG systems, run against rag-support-utomation
- github.com
Voice Ai
Full-duplex voice agent with measured barge-in.
- github.com
Ai Doctor
Document intelligence and grounded RAG platform over PDF, DOCX, PPTX, XLSX, HTML and Markdown. Hybrid retrieval with RRF fusion, reranking, and a measured refusal gate. Answers cite the file and page, or refuse. Runs offline with no API key.
- github.com
Intent Classification Lab
Intent classification three ways on identical splits: TF-IDF baseline, a Transformer written from scratch in PyTorch, and a fine-tuned pretrained encoder. The baseline wins, and the README explains why.
- github.com
Webdocs Mcp
Crawl, index, and hybrid-search documentation sites; served to LLM agents as an MCP server. FastAPI + DuckDB + BM25/embeddings, fully offline-testable.
- github.com
Enterprise Ai Platform
AI copilot for enterprises: RAG chat, a router over six task handlers, hybrid search, admin analytics, and MLOps.