Sai Chandra Bandi

About

Built and productionized a real-time enterprise RAG pipeline to improve factual accuracy and reduce LLM hallucinations by grounding responses in constantly changing internal knowledge bases (policies, manuals, FAQs). Experienced in orchestrating end-to-end ML workflows (Airflow/Kubernetes), handling messy multi-format data with schema enforcement (Pydantic/Hydra), and maintaining freshness via streaming incremental embeddings plus batch refresh. Also delivers applied ML solutions with non-technical teams (marketing/CRM) for segmentation and personalized engagement.

Key Strengths

• Built and deployed real-time RAG system to reduce hallucinations and keep answers aligned to constantly changing enterprise knowledge bases
• Strong data engineering for messy multi-format sources (JSON, PDFs, SQL) using automated validation and schema enforcement
• Designed two-tier update strategy (streaming incremental embeddings + off-peak batch refresh) to balance freshness and performance
• Workflow orchestration expertise (Airflow/DAGs) with attention to retries, concurrency limits, and resource tuning
• Reliability-focused AI development with defined metrics, automated testing, stress tests, and real-world evaluation (A/B tests, feedback loops)
• Effective cross-functional delivery with non-technical stakeholders (marketing/CRM), translating ML concepts and shipping usable tooling

Experience

Education

Skills

Languages