Available for new opportunities

Lead data scientistbuilding intelligentclinical AI systems.

I'm Abjasree — 4+ years turning unstructured healthcare data into business-impactful solutions with GenAI, clinical NLP, and computer vision. I build scalable pipelines that raise accuracy and cut manual review time.

Start a conversation Download résumé

01 — About

A data scientist who turns messy data into decisions.

I'm a Lead Data Scientist with 4+ years of experience turning unstructured healthcare data into business-impactful solutions. Specializing in generative AI, LLMs, and clinical AI, I build scalable NLP and CV pipelines that enhance accuracy, reduce manual review time, and drive operational efficiency.

My work spans from radiomics-based diagnostics to AI-powered document processing and therapy-outcome analytics, delivering measurable improvements in healthcare systems. I'm passionate about transforming unstructured medical data into actionable insights that accelerate healthcare decision-making.

roleLead Data Scientist · DATYCS
stackPython · PyTorch · AWS · Azure
basedIndia · open to remote
superpowerturning unstructured data into clinical insight

02 — Work

Where I've shipped things that mattered.

DATYCS
Lead Data Scientist · Remote
Apr 2024 — Present
- Led a 6-member GenAI & Research squad; built AWS/Azure CI/CD reducing model roll-out time by −80% (3 weeks → 5 days).
- Architected & deployed 3 transformer-based NLP/CV pipelines processing 10K+ AML/CLL charts into Snowflake, boosting throughput +35%.
- Fine-tuned TrOCR for handwritten prescriptions, improving accuracy +25% and enabling real-time medication safety alerts.
- Deployed Vision LLM on Azure to parse multi-handwriting prior-authorization forms into structured JSON (+28% accuracy, −45% manual review).
- Leveraged autonomous AI agents for patient-specific search validation and clinician response generation (+30% accuracy, −40% reply time).
- Partnered with Eversana to analyze AML & CLL therapy-switch drivers and adverse effects, shaping pharmaceutical market-access strategies.
IIT Madras
Data Scientist · Chennai
Aug 2022 — Mar 2024
- Automated analysis of 1,000+ CT/MRI images, reducing manual preprocessing time by −80%.
- Increased renal calculi & pulmonary nodule diagnostic accuracy by +18% using CNN + radiomics + Bayesian-optimized XGBoost.
- Deployed QA models at Apollo Proton Cancer Center, cutting turnaround −10% and flagging 12 high-risk plans per quarter.
Univ.AI
Teaching Assistant · Part-time
Dec 2021 — Aug 2022
- Assisted in teaching machine learning and data science courses to students from diverse backgrounds.
- Mentored students in practical ML projects and helped them understand complex AI/ML concepts.
- Contributed to curriculum development and course material preparation.

03 — Projects

Research that left the lab.

Radiomics for NSCLC Classification

Oct 2023 — Jan 2024 · Publication

Built radiomics model with 83% accuracy for differentiating adenocarcinoma and squamous cell carcinoma in non-small cell lung cancer beyond nodule morphology in chest CT. Decision-curve analysis showed net clinical benefit across thresholds.

RadiomicsMachine LearningMedical Imaging

Zero-Shot Image Registration (ZSIR-FE)

Sept 2022 — Oct 2023 · Med-NeurIPS 2023

Designed DNN feature-based registration improving Dice score by +0.30 and running 6× faster than SIFT on BRaTs dataset through feature extraction approach.

Deep LearningComputer VisionMedical Image Registration

Pulmonary Nodules Classification

Sept 2022 — Oct 2023 · Publication

Engineered radiomic features + XGBoost on limited Indian dataset, achieving 89% accuracy (+10% vs prior studies) for pulmonary nodules classification from chest CT scans.

XGBoostFeature EngineeringMedical AI

Automatic Detection of Renal Calculi

Sept 2022 — Jul 2023

Processed 163 CT scans and built deep-learning pipeline reaching 85% accuracy (+25 pp improvement); slated for clinical deployment.

Deep LearningMedical ImagingClinical AI

Elliptic Flow of Light Nuclei

May 2019 — June 2020 · MS Thesis

Simulated heavy-ion collisions with AMPT; computed elliptic flow using STAR detector data for light nuclei. Developed C++ macros to compare Coalescence models with experimental measurements, achieving thesis distinction. Also worked on simple ML classification models to distinguish signals and background.

HPCC++Machine Learning

04 — Skills

Tools, languages, and domains I reach for.

programming · ml

Languages & Frameworks

PythonSQLC++RMATLABPyTorchTensorFlowHugging FaceScikit-LearnLangChain

cloud · mlops

Cloud & MLOps

AWS SageMakerAWS S3Azure MLAzure FunctionsSnowflakeDockerCI/CD

domains · research

AI/ML Domains

GenAI & LLMsClinical NLPComputer VisionRAGAI AgentsReinforcement Learning

05 — Credentials

Certifications & education.

Certifications

AWS Certified ML Engineer — Associate Early Adopter

Amazon Web Services · Dec 2024

AWS Certified ML Engineer — Associate

Amazon Web Services · Dec 2024 → Dec 2027

Event-Driven Agentic Document Workflows

DeepLearning.AI · Mar 2025

Machine Learning

Coursera · Oct 2021

Sequence Models

Coursera · Oct 2021

Algorithmic Toolbox

Coursera · Nov 2021

Education

Indian Institute of Science Education and Research, Tirupati

BS MS Dual Degree · CGPA: 8.0

2015 — 2020

G. H. S. S. Palakkad

Higher Secondary · Percentage: 97.33%

2013 — 2015

Jawahar Navodaya Vidyalaya (JNV)

High School · CGPA: 10

2012 — 2013

06 — Contact