Rakesh Kolagani

About

AI/ML engineer with production experience building a RAG-based internal analytics assistant (Databricks + ADF ingestion, Pinecone vector store, LangChain orchestration) deployed via Docker on AWS SageMaker with CI/CD and MLflow. Strong focus on real-world constraints—latency/cost optimization (LoRA ~60% compute reduction), hallucination control with citation grounding, and enterprise security/governance. Previously at Intuit, delivered an interpretable churn prediction system (PySpark/Databricks, Airflow/Azure ML) that improved retention targeting ~12%.

Experience

Education

Key Strengths

• Built and deployed production RAG internal assistant across Snowflake/SharePoint with citation-grounded responses
• Optimized LLM latency/cost using LoRA, reducing compute costs ~60%
• Implemented hallucination controls via retrieval grounding and enforced source citations
• Strong MLOps/production deployment experience (Docker on SageMaker, CI/CD with GitHub Actions, MLflow tracking)
• Designed secure AI systems with IAM-based access, masking, encryption, and exclusion of sensitive data from fine-tuning
• End-to-end orchestration expertise with Airflow and Azure Data Factory; improved data freshness ~30% via hybrid orchestration
• Structured evaluation approach for LLM/agent workflows (metrics, modular testing, A/B + human review, monitoring/alerts)
• Translated non-technical stakeholder goals into measurable ML outcomes; delivered churn model with SHAP + Power BI interpretability
• Business impact: improved retention targeting ~12% and reduced manual report turnaround time