# Dr Shashidhar Ameenpur **Data & Research Engineer** — London, United Kingdom > Data & Research Engineer with an MSc in Health Data Science and Microsoft Fabric certification, specializing in clinical data pipelines, wearables analytics, and signal processing. Career Archetype: **Junction Trailblazer** (HE-MG) — One of the first Junction Trailblazers on Saywise ## Links - LinkedIn: https://linkedin.com/in/dr-shashidhar-ameenpur-86130253 ## Experience ### Data Engineering Apprenticeship, Cambridge Spark (2025-02 – 2026-08) London · Developed scalable data architecture, streaming systems, and cloud-native engineering capability through applied delivery. Built ingestion frameworks, data lakes, real-time pipelines, and automated orchestration workflows. Applied Python, SQL, Spark, and Docker to production-oriented data engineering projects. ### Clinical Data Analyst, South London and Maudsley NHS Foundation Trust (2022-02 – present) London, England, United Kingdom · Built clinical datasets and automated analytics pipelines using SQL, Python, and Azure services. Designed and deployed an end-to-end automated report generation pipeline for Empatica E4 wearable data—processing accelerometer, BVP, EDA, HR, and temperature signals from AWS S3, applying signal cleaning and feature extraction in Python, orchestrating via Luigi, and generating patient-level clinical reports in R. Reduced per-patient processing from hours of manual work to a fully automated workflow. ### Sr. Content Lead - Payment Policy & EMR Data, Cotiviti (2014-10 – 2020-02) Hyderabad, Telangana, India · Maintained clinical payment rules and developed new rules per regulatory guidelines and client requests. Created and managed SQL Server tables for EMR health data across EPIC and MedTech systems. Ran stored procedures and updated tables to maintain data quality across large-scale clinical datasets. Collaborated with clinical and engineering stakeholders to translate policy requirements into data-layer logic. ### HCC Medical Coding Specialist, UnitedHealth Group (2012-04 – 2013-06) London · Performed Hierarchical Condition Category (HCC) medical coding to support risk adjustment and CMS reimbursement accuracy. Reviewed clinical documentation to assign accurate ICD-10 codes aligned with HCC model requirements. Supported quality audits and coding reconciliation processes to ensure compliance with CMS guidelines. ## Education ### Data Engineer Level 5, Cambridge Spark (2025-02 – 2026-08) Distinction ### Msc Health data science in Data Science, Swansea University (2021-09 – 2022-01) Health Data Science, R, Phyton, SQL ### bachelor of ayurveda medicine and surgery in Ayurvedic Medicine/Ayurveda, Rajiv Gandhi University of Health Sciences (2004-01 – 2009-01) ## Projects ### NHS Automated Report Generation Pipeline End-to-end wearable data processing and clinical reporting system · Designed and deployed automated pipeline processing Empatica E4 wearable data (accelerometer, BVP, EDA, HR, temperature) from AWS S3. Applied signal cleaning and feature extraction using Python (pandas, scipy), orchestrated task workflows via Luigi, and generated patient-level PDF reports using R and RHRV for HRV analysis. Implemented PHI redaction layer using Presidio and NuExtract with AWS Secrets Manager for security. ### AWS S3 Data Engineering Pipeline Cloud-native data ingestion and processing framework · Built scalable ingestion framework and data pipeline leveraging AWS S3 for storage and Python/Spark for processing. Implemented automated orchestration and validation workflows as part of Cambridge Spark apprenticeship. ### Time-Series Feature Engineering - Empatica Wearable Data Signal processing and feature extraction from wearable devices · Developed feature extraction pipeline for physiological time-series data from Empatica E4 wearables. Applied signal processing techniques to clean raw sensor data and generate clinical-grade features for downstream analytics and research applications. ### Local PHI Redaction Tool On-device sensitive data masking for clinical documents · Built local PHI redaction tool combining Presidio, OCR, and NuExtract (via Ollama) to identify and mask sensitive information in clinical documents. Designed for on-device processing to maintain data privacy without external API calls. ### Automated Multi-File PowerPoint Table Extractor Batch extraction and processing of structured data from presentations · Developed Python utility to extract tables from multiple PowerPoint files, enabling automated data consolidation and transformation from presentation formats into structured datasets. ## Skills Data Engineering, Data Pipelines, Extract, Transform, Load (ETL), Data Governance, Data Integration, Ingest and transform data, Implement and manage an analytics solution, Monitor and optimize an analytics solution, R (Programming Language), Transact-SQL (T-SQL), SQL, Microsoft Power BI, Electronic Medical Record (EMR), Microsoft Azure, Data Analysis, Python (Programming Language), Healthcare Management, Healthcare Consulting, Medical Coding, Healthcare, Revenue Cycle, Healthcare Industry, ICD-9, Medical Billing, Medicaid, Working with Physicians, ICD-10, Data Analytics, Search Engine Technology, Generative AI, PySpark, Spark, AWS S3, Secrets Manager, Snowflake, ELT, Data Lakes, Luigi, Docker, Data Validation, Warehousing, Time-Series Analysis, Wearables, HRV Analysis, Signal Processing, Clinical Data, EPIC, MedTech, HCC Coding, CMS Policy, Presidio, NuExtract, Ollama, pandas, scipy, RHRV, Data Architecture, Orchestration, Cloud Services ## Credentials - **Microsoft Certified: Fabric Data Engineer Associate** — Microsoft - **AWS AI Practitioner Challenge** — Udacity (issued 2026-03) - **Associate Data Engineer in Snowflake** — DataCamp (issued 2025-11) - **Collaboration, Marketplace & Cost Estimation Workshop** — Snowflake (issued 2025-10) - **Hands-On Essentials: Data Engineering Workshop** — Snowflake (issued 2025-10) - **Hands-On Essentials: Data Warehousing Workshop** — Snowflake (issued 2025-10) - **Generative AI: The Evolution of Thoughtful Online Search** — LinkedIn (issued 2023-06) - **Microsoft Certified: Azure AI Fundamentals** — Microsoft (issued 2021-06) - **Microsoft Certified: Azure Data Fundamentals** — Microsoft (issued 2021-06) - **Microsoft Certified: Azure Fundamentals** — Microsoft (issued 2021-06) - **Microsoft Excel (Microsoft 365 Apps and Office 2019)** — Microsoft (issued 2021-06) - **SAS Programming 1: Essentials** — SAS (issued 2021-06) - **Data Fluency: Exploring and Describing Data** — LinkedIn (issued 2020-06) - **Learning Data Analytics** — LinkedIn (issued 2020-06) --- Source: https://saywise.com/member2233 (last modified 2026-10-06T12:21:47.581Z)