Sai Addala

About

Built and productionized an LLM-powered financial intelligence and forecasting platform at Northern Trust using a RAG architecture (LangChain + Hugging Face + FAISS) with end-to-end MLOps (Docker/Kubernetes, Airflow, MLflow). Emphasized regulatory-grade explainability (SHAP/Power BI) and hallucination control (retrieval-only grounding), achieving ~30% forecasting accuracy improvement and ~65% reduction in analyst research time, with sub-second inference and 95% uptime on EKS/AKS.

Experience

Education

Key Strengths

• Built and deployed production LLM/RAG platform for financial risk/portfolio users
• Delivered measurable business impact: ~30% increase in portfolio forecasting accuracy
• Delivered measurable productivity gains: ~65% reduction in analyst manual research
• Strong hallucination-mitigation approach (retrieval-only grounding, similarity thresholds, 'no answer' fallback, offline eval)
• Production MLOps and orchestration at scale (Dockerized microservices on Kubernetes with Airflow/MLflow)
• High-reliability, low-latency deployment experience (95% uptime, sub-second inference) using autoscaling and blue-green deployments
• Rigorous evaluation methodology (adversarial + unit/integration tests, A/B testing, drift monitoring, automated retraining)
• Effective collaboration with non-technical stakeholders; translated needs into explainable dashboards and NL query workflows