Akshit Modi

About

Healthcare/clinical ML practitioner who built and productionized ClinicalBERT-based pipelines to extract and standardize oncology EHR data, improving downstream model F1 from 0.81 to 0.92 while controlling training cost via LoRA/QLoRA. Experienced orchestrating real-time AWS ETL/ML workflows (Glue, Lambda, SageMaker) and partnering with clinicians using SHAP-based interpretability, contributing to an 18% reduction in readmissions and full adoption.

Experience

Education

Key Strengths

• Improved downstream ML performance by raising F1 from 0.81 to 0.92 via EHR standardization and data quality work
• Healthcare NLP experience extracting oncology EHR data from unstructured/mixed sources
• Cost-efficient model fine-tuning using LoRA/QLoRA
• Strong data quality and schema normalization practices using clinical vocabularies (ICD, SNOMED CT, RxNorm) and validation metrics
• Production-oriented AWS ML/ETL orchestration (Glue, Lambda, SageMaker) including event-driven pipelines
• Rigorous AI/agent evaluation approach (KPIs, sandboxing, integration/regression tests, human-in-loop, A/B tests, drift monitoring, rollback)
• Effective collaboration with clinicians using interpretable ML (SHAP), leading to 18% reduction in readmissions and adoption