Sravan Kumar Jajam

About

ML/GenAI engineer with production experience building an LLM-powered governance layer that summarizes verified drift/performance signals into validation reports and release notes, designed for regulated environments with de-identification and non-blocking fallbacks. Strong Airflow-based orchestration background across healthcare and finance, integrating Databricks/Spark and MLflow for scalable retraining/monitoring. Demonstrated ability to partner with non-technical healthcare operations teams to deliver actionable risk-scoring outputs via dashboards and automated reporting.

Experience

Education

Key Strengths

• Built and deployed a production LLM layer for ML workflow validation summaries and release notes using structured inputs
• Strong reliability/governance approach in regulated environments (de-identified inputs, non-blocking LLM step, deterministic fallbacks)
• Hallucination mitigation via constrained prompts and deterministic output validation; prompt versioning like code
• Deep orchestration experience with Apache Airflow for end-to-end ML pipelines (ingestion through training/inference and delivery)
• Scales ML workflows by modular, idempotent DAG design and pushing heavy compute to Databricks/Spark
• Pragmatic evaluation mindset: measures impact via workflow metrics (manual review time reduction, consistency, latency, intervention rates)
• Effective cross-functional delivery: translated healthcare risk model outputs into actionable tiers/explanations via dashboards and reports