Clinical Data & ML Engineering

Pawan
Rama Mali

I build clinical data platforms and machine learning systems for life sciences, and still write the core code.

Scroll
01 / About

I build clinical software that ships and holds up under audit.

In short

Ten years building clinical data platforms and machine learning systems for pharmaceutical and biotech teams. I still write the code that goes to production, not only the plan for it.

Clinical dataLLM & agentsR / PythonCDISCMLOps
In practice

Most of it is retrieval systems and agents over patient-level clinical data. Every answer cites the record it came from, sits behind guardrails, and reaches a human reviewer before anyone acts on it. The stack is Python, R, SQL and PostgreSQL on AWS, shipped with Docker and CI/CD.

Underneath sits the clinical detail: CDISC SDTM and ADaM, legacy SAS rebuilt as validated R, risk-based quality monitoring and biomarker analytics, all under GxP. I also build in the open. I founded R4SUB, a seven-package ecosystem for submission readiness, and have authored ten R packages, nine of them on CRAN.

0+
Years building production software
0
Open-source R packages authored
0
Published on CRAN
0
Packages in the R4SUB ecosystem
02 / Experience

Where I have built.

Ten years across clinical data products, engineering analytics and applied machine learning, most of it client facing and in audited environments.

  1. 2024 → Present

    Technical Lead, Clinical Data & Applied ML

    TechWorksLab, embedded engineering for global pharma and biotech clients

    PythonRFastAPIPostgreSQLCDISC
  2. 2022 → 2023

    Engineer, Scientific & Clinical Data Products

    Appsilon, R and Shiny data products for pharmaceutical and research teams

    R ShinyR packagesCI/CD
  3. 2016 → 2022

    Technical Lead, Engineering Analytics

    AERODESIGN Solutions, full-stack analytical platforms and team leadership

    RPythonData pipelines
  4. 2013 → 2014

    Data Analyst

    First Advantage, large-scale data validation, QC and statistical reporting

    StatisticsReporting
Currently

Technical Lead at TechWorksLab

Leading in-house clinical application, analytics and ML delivery for sponsor clinical development, while staying hands-on in the code.

  • Retrieval and agent systems over patient-level data, on self-hosted models
  • Risk-based quality monitoring and biomarker analytics platforms
  • Legacy SAS converted to validated R under parallel-run evidence
  • Mentoring engineers and statistical programmers toward ownership
03 / Skills

Capabilities, grouped.

LLM & Agent Systems

Retrieval, agents and tool use, evaluation sets, guardrails and human review gates; model APIs and custom MCP servers.

Self-Hosted & Applied ML

Open-weight inference (GGUF, llama.cpp, MedGemma); PyTorch, scikit-learn, transformers; vision ensembles (CoAtNet, ConvNeXt, DINOv2).

R & Shiny Engineering

Expert R, production Shiny (modules, performance), CRAN package authorship, testthat, renv and reproducible environments.

Clinical Data Standards

CDISC SDTM and ADaM, Define-XML, controlled terminology, admiral and pharmaverse, RBQM and KRI frameworks.

Statistical Programming & SAS

SAS and SAS to R migration under validation, TFL shells and specifications, QC and double programming.

Backend & Data Engineering

Python (FastAPI, plumber), REST API design, PostgreSQL, MongoDB, ETL and ELT, metadata-driven pipelines.

Cloud, DevOps & Validation

AWS, Azure, Docker, Linux, CI/CD (GitHub Actions, GitLab), Posit Connect; GxP and 21 CFR Part 11.

Biostatistics & Multi-Omics

SAPs, survival, mixed-effects and Bayesian models; genomics, transcriptomics, proteomics; DESeq2, limma, edgeR, GSEA.

04 / Selected Work

Systems shipped.

Clinical data platforms, machine learning and engineering tooling. Client work is shown anonymized. A cross-section, not an exhaustive list.

01

Clinical Review Agent

Lead · Global pharma sponsor

Retrieval-grounded summarization over patient-level records on self-hosted MedGemma, so data never leaves the network. Every statement carries a sentence-level citation, behind guardrails and a human review gate.

PythonMedGemmaRAGRShiny
02

Risk-Based Quality Monitoring

Lead Engineer · Global pharma sponsor

Scores and ranks trial sites and participants by risk, so oversight effort goes where the signal is. Indicator drill-down from study to site to subject, statistical thresholds, evidence tables and recalculation driving investigation.

PythonRSQLStatistical modelingRBQM
03

Conformance Review Assistant

Proof of Concept

Checks clinical datasets against CDISC SDTM, Define-XML and FDA conformance rules. Rules run deterministically and the model only explains each finding, giving a reason and a remediation path, which keeps it auditable.

PythonRCDISC SDTMDefine-XML
04

Biomarker Analytics Platform

Senior Developer · Global pharma sponsor

Interactive biomarker visualization for exploratory analysis: spaghetti, box, volcano and heatmap plots with dynamic filtering and subgroup analysis. Re-engineered rendering and caching to hold interactivity on large datasets.

RShinyJavaScriptD3.jsSQL
05

Trial Visualization & Patient Analytics

Senior Developer · Global pharma sponsor

Demographics, disposition and treatment dashboards with patient timelines spanning adverse events, labs, medications, history and vital signs. Authored ADaM specifications and derivations with study-day logic and subgroup analysis.

RShinyADaMSDTM
06

Traceability Engine

Solution Architect

Metadata-driven lineage platform linking Statistical Analysis Plans, analysis datasets and TLF outputs back to source metadata, with automated lineage tracking and traceability validation.

RPythonCDISC ADaMSDTM
07

Applied ML Research: Vision & Reasoning

Independent

Medical image abnormality detection on the RSNA knee dataset with CoAtNet, ConvNeXt and DINOv2 ensembles. Antimicrobial peptide activity, MIC regression and hemolysis prediction; reasoning agents and evaluation for ARC-AGI.

PyTorchComputer VisionTransformers
08

Clinical Trials Reporting System

Lead Developer

End-to-end CDISC SDTM, ADaM and TLG reporting with automated Clinical Study Report generation. Cut report time from six weeks to two days.

RR MarkdownSASGitLab CI/CDDocker
09

CliniTransformR: SDTM/ADaM Suite

Lead Developer & CDISC Specialist

R package suite converting raw clinical data into compliant SDTM and ADaM formats, with 200+ validation rules and automated compliance checks.

RCDISCValidation
10

ModelBox: Self-Hosted Inference Server

Software Architect

Self-hosted ML inference server with GPU acceleration, load balancing and API management. Sub-100ms inference at 10k+ concurrent requests.

FastAPIPythonDockerGPURedis
11

Image Prediction REST API

Backend Developer & API Architect

Production RESTful API serving image-classification models. Responses under 200ms, JWT authentication, and horizontal scaling to 1000+ images concurrently.

R PlumberRESTMongoDB
12

Reusable Shiny UI Component Library

Component Architect

50+ reusable Shiny UI components (modals, notifications, data grids, loading states) with a theming system. Adopted by 25+ applications.

R ShinyCSS3JavaScript
13

CI/CD Automation for Shiny

DevOps Engineer

CI/CD for R Shiny: quality checks, automated tests, Docker builds, security scans and multi-environment deploys with rollback. 99.5% success across 100+ releases.

GitLab CI/CDDockerDevOps
14

RMarkdown Reporting Engine

Automation Engineer

Parameterized RMarkdown reporting wired into CI/CD for consistent, reproducible clinical and operational reports. 2000+ generated across 50+ report types.

R MarkdownCI/CD
15

ScrapText: Web Scraping & Text Mining

NLP Engineer

R package combining web scraping with text mining and sentiment analysis. Adaptive rate limiting, topic modeling, and 92% sentiment accuracy across 1000+ sites.

Rrvesttmtidytext
16

Conversational Support Bot

NLP Developer

Neural-network chatbot for customer support and FAQ automation. Context-aware replies, five languages, and routing of complex questions to specialists. 89% intent accuracy.

PythonNeural networksNLP
17

Learning Management System

Full Stack Developer

Secure corporate LMS for training and certification: courses, automated assessments, digital badges and enterprise SSO. 500+ learners.

PythonDjangoPostgreSQL
18

R / Python Hybrid Pipelines

Integration Developer

Bridges between R and Python pairing R statistics with Python machine learning. Two-way data exchange with type conversion, validation and tuned memory management.

RPythonData pipelines
05 / Open Source & Products

Built in the open.

Packages and ecosystems I author and maintain. Nine are published on CRAN.

R4SUB

Open Source
Founder & Lead Author

An open-source R ecosystem scoring clinical data readiness for regulatory submission. An ADaM-to-SDTM traceability engine, FMEA-based risk quantification and a Submission Confidence Index turn binary pass or fail checks into scores a reviewer can trace. Sole author and maintainer.

7Packages on CRAN
6Authorities
r4sub.github.io

edgemodelr

CRAN v0.7.0
Author & Maintainer

Local large language model inference inside R through GGUF model files and the llama.cpp engine, with completion and streaming and no cloud call. Built for environments where data cannot leave the network.

16+GitHub stars
CRANPublished
cran.r-project.org/package=edgemodelr

shinypayload

CRAN v0.1.0
Author & Maintainer

HTTP POST and query-parameter ingestion into Shiny applications as reactive values. Cross-platform and MIT licensed.

132Tests
MITLicense
cran.r-project.org/package=shinypayload

databoxR

R Package
Author

An interactive clinical dataset explorer for SDTM and ADaM data. Browse, filter and inspect analysis-ready datasets without leaving R.

SDTM& ADaM
ShinyInterface
github.com/PawanRamaMali
06 / Education & Certifications

Academic path & credentials.

Education
  1. 2025 → Present

    Research Scholar

    Indian Institute of Technology (IIT) Ropar

  2. 2022

    M.Tech, Artificial Intelligence

    REVA University

  3. 2016

    B.Tech, Aerospace Engineering

    Hindustan Aviation Academy

Certifications
  • DeepLearning.AI, Probability & Statistics for ML & Data Science · 2025
  • Genentech, Making Data Science Work for Clinical Reporting · 2025
  • Stanford Online, Supervised Machine Learning: Regression & Classification · 2024
  • Skillsoft, Establishing Guardrails & Governance · 2024
  • Docker, Inc, Docker Foundations Professional Certificate · 2024
  • LinkedIn, Data Pipeline Automation with GitHub Actions (R & Python) · 2024
  • Open Source in Pharma, Pharmaverse Champion & Intro to tidymodels · 2023
  • Microsoft Certified, Azure AI Engineer Associate · 2022
07 / Contact

Let's build something clear.

Open to clinical data and machine learning engineering, consulting, and collaboration. The fastest way to reach me is email.