Looking for a job

Srilekha Manjunath

@srilekhamanjunath

AI/ML Engineer at McKesson Health who shipped an enterprise RAG assistant serving 500+ employees.

At McKesson Health, I shipped an Enterprise RAG Knowledge Assistant using LangChain, FAISS, and Azure OpenAI. It serves 500+ employees and cut average query resolution time by 35%.

At HCLTech, I designed and deployed a CNN-based quality-inspection model for a furnace manufacturing line, cutting manual inspection time by 40% and defect-escape rates by 18%. I’ve also delivered forecasting, predictive-maintenance, and production ML systems across healthcare and enterprise domains.

Experience

Work history, roles, and key accomplishments

Current

AI/ML Engineer

Current

McKesson Health

Aug 2025 - Present (1 year 2 months)

Architected and shipped an Enterprise RAG Knowledge Assistant serving 500+ employees, cutting query resolution time by 35%. Owned the full ML lifecycle of a demand-forecasting pipeline, improving forecast accuracy by 22%.

Lang Chain Faiss Azure OpenAI Hugging Face XGBoost AWS Sagemaker Python Docker Kubernetes SHAP LIME PII Masking Agile

AI/ML Engineer

HCLTech

May 2021 - Jul 2024 (3 years 2 months)

Designed and deployed a CNN-based computer vision quality-inspection model, cutting manual inspection time by 40% and reducing defect-escape rate by 18%. Built predictive-maintenance models on sensor data, increasing equipment uptime by 15%.