Skip to content
View StringAna's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report StringAna

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
StringAna/README.md

Antara Tewary

Senior Machine Learning Engineer building production ML systems for healthcare applications.
MS in Computer Science (ML Concentration, GPA 4.0) | George Mason University | May 2025


Currently Building

Senior ML Engineer @ AIMindSystems Foundation — Leading architecture for an assisted healthcare platform

Clinical validation system using MedGemma + BioClinicalBERT with LangGraph orchestration — achieving >95% precision and <5% false acceptance across 10k+ summaries
FHIR ingestion pipeline with Pydantic validation and PostgreSQL — reduced data-prep latency from 3–4 weeks to 48 hours for 10k+ records
FAISS retrieval system for LoRA-tuned MedGemma — <2s query latency, improved clinical field accuracy from 68% to 87%
Multi-stage evaluation & drift monitoring — automated retraining triggers, reduced physician review time from 5–6 hours to ~20 minutes per case


Selected Highlights

Dual-model clinical validation — LangGraph-orchestrated MedGemma/BioClinicalBERT system with field-level UUID checks, >95% precision on 10k+ clinical summaries

Mitra: University resource platform — Lambda-driven ingestion with GPT-3.5 evaluators and Glue ETL workflows, 70% storage reduction, 85% retrieval accuracy, 38% Lambda cost reduction with zero regression

Pylinguist research (in revision for ICER 2026) — multi-stage code translation pipeline processing 550K+ Python samples across 7 languages, 85% BLEU score and 98% semantic similarity

Mercedes-Benz segmentation & forecasting — PySpark-based k-means clustering, ARIMA models with 84% forecast accuracy, BERT multilingual review processing reducing critical issue identification time from 8 days to 2–3 days


Research & Community

Research: Pylinguist code translation pipeline (ICER 2026 revision) — 85% BLEU across 7 languages with bidirectional validation

Community: Co-Lead, Google Developer Group @ GMU (Aug 2024 – May 2025) — co-founded GMU's first GDG chapter, grew to 100+ members, organized bi-weekly ML/AI workshops on RAG systems and prompt engineering

Awards: Distinguished Academic Achievement Award by College of Engineering and Computing | Class of 2025 Commencement Speaker

Certifications: AWS Certified Developer Associate (DVA-C02) | AWS Certified Machine Learning Engineer Associate (MLA-C01)


🌐 Connect

LinkedIn Email


💻 Tech Stack

Machine Learning & AI

PyTorch scikit-learn TensorFlow Keras NumPy Pandas Matplotlib SciPy

Cloud & Infrastructure

AWS Apache Spark Apache Hadoop Docker Git

Languages & Frameworks

Python JavaScript FastAPI NodeJS React

Data & Databases

PostgreSQL MongoDB Redis Amazon DynamoDB

Tools & Others

OpenCV Streamlit Jupyter LaTeX


📊 GitHub Stats



🏆 GitHub Trophies


Pinned Loading

  1. leetcode-calendar leetcode-calendar Public

    Forked from ankitkr8540/leetcode-calendar

    NPM package for showing the calendar by passing the username

    JavaScript

  2. PET_Reproducibility_Study PET_Reproducibility_Study Public

    Forked from timoschick/pet

    This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"

    Python

  3. PyLinguist PyLinguist Public

    Making Python accessible to different language speakers

    HTML 1

  4. TCQA-Reproducibility-Study TCQA-Reproducibility-Study Public

    Forked from sonjbin/TCQA

    Data and code for "Time-Aware Representation Learning for Time-Sensitive Question Answering"

    Python

  5. WorkspaceArchiver WorkspaceArchiver Public

    Forked from lingyundai/workspace-archiver

    TypeScript

  6. pylinguist-paper pylinguist-paper Public

    Forked from ankitkr8540/pylinguist-paper

    Python