Astha Garg
AI Development Architect at Lenovo
Singapore
Summary
👤
Senior🎓
Top SchoolAstha Garg is an AI Development Architect and builder-scientist with a decade of experience turning complex datasets—time-series, IoT, and natural language—into production-grade AI products across chemicals, semiconductors, retail and sustainability. She blends deep research (PhD-level work on time-series anomaly detection published in TNNLS) with hands-on engineering, having led teams to deliver RAG-based chatbots, recommendation systems, and scalable ML modules that cut manual work by up to 80%. At companies from A*STAR and Citrine to Terrascope and Lenovo she has driven end-to-end solutions from concept to continuous product while partnering closely with business, product and domain experts. Her recent focus is on generative-AI, multi-agent systems and robust LLM engineering for real-world deployments. Notably, she bridges lab-scale experimentation and field-ready systems—automating large-scale data pipelines and evaluation protocols informed by thousands of experiments. Based in Singapore, she’s equally comfortable as scientist, product engineer, and pragmatic builder who prioritizes measurable business impact.
10 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Chemical Engineering, Doctor of Philosophy (Ph.D.) Chemical Engineering at Penn State UniversityIndian Institute of Technology BombayMatriculation, Matriculation at J. H. Ambani School
Bengali, Hindi, English
Github Skills (29)
autoencoder10
residual-networks9
anomaly-detection9
time-series8
evaluation8
prediction-model7
deep-learning7
uncertainty6
regression6
machine-learning6
classification6
wikipedia6
random-forest5
keras5
recurrent4
Programming languages (4)
Github contributions (5)
astha-chem/mvts-ano-eval
Jul 2021 - May 2022
A repository for code accompanying the manuscript 'An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series' (published at TNNLS)
Contributions:1 review, 5 commits, 2 PRs in 10 months
autoencoderanomalydeep-learninganomaly-detectionevaluation
astha-chem/Decathlon-Residual-Adapters-Keras
Dec 2017 - Feb 2018
Contributions:48 commits, 39 pushes in 1 month
residual-networksdeep-learningresidualtensorflowkeras
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.