☁️

✦✦✦✦✦✦✦✦

For recruiters 🧑🏽‍💻

Builds the product and the case for it: discovery that starts from the job to be done, a success metric fixed before the results, and a decision at the end. Three AI products live, among them a refund-first complaint queue for banks and a lease check for NYC renters, plus the readout of a 64,000-customer email experiment.

🔍

read, then matched against her projects and skills, gaps and all ✦

hiring for:

From the résumé 📄

Education

Columbia University

New York, NY

M.S. Data Science, GPA: 3.9/4.0

Aug 2025 - Expected Dec 2026

Coursework: Deep Learning, Generative AI Systems, Agentic AI, High Performance Computing, Causal Inference, Statistical Inference
Teaching Assistant for Natural Language Processing and AI for Public Policy; Data Science Institute Student Council Member

Vellore Institute of Technology

Vellore, IN

B.Tech. Computer Science and Engineering (Data Science specialisation), GPA: 4.0/4.0

Jul 2019 - May 2023

Ranked 7th out of 200 (Top 4%); Merit Scholarship recipient (2019-2023); Program Representative (2019-2023)
Coursework: Machine Learning, Artificial Intelligence, Natural Language Processing, Image Processing, Social Information Networks

Skills

Programming & Frameworks: Python, SQL, R, C++, PyTorch, TensorFlow, scikit-learn, FastAPI, NumPy, Pandas

LLM & AI Systems: RAG, LangChain, Hugging Face, ChromaDB, FAISS, Multimodal AI, Prompt Engineering, Agent Workflows

Data Engineering & Infrastructure: Databricks, PySpark, MongoDB, MySQL, BigQuery, Redis, Docker, Git, REST APIs

Cloud & MLOps: AWS, Azure DevOps, Weights & Biases, CI/CD, Experiment Tracking, Feature Engineering, Model Monitoring

Work Experience

NYC Administration for Children's Services (ACS)

New York, NY

Predictive Analytics Intern

Jun 2026 - Aug 2026

Built an explainability framework for a child welfare risk model on 900K+ records, transforming black-box predictions into transparent, policy-driven decisions through configurable operating thresholds spanning 25-80% recall (0.799 ROC-AUC, 7.2× base-rate precision).
Designed a three-level reliability audit proving explanations reproducible across evaluation sets (ρ=0.991), then established via noise-control testing that only 15 of 149 features carried real signal, setting a defensible limit on what the agency can claim from any feature ranking.

Shell

Bengaluru, IN

Software Engineer

Aug 2023 - Jul 2025

Developed machine learning forecasting solutions in Databricks (PySpark, SQL) across 12 business units, reducing forecast error by 23% and enabling $100K+ annual cost optimization decisions.
Built production data pipelines, feature engineering workflows, and 5 Blue Prism RPA bots with logging and retry logic, cutting manual reporting effort by 85% (120+ hours/quarter) and improving SLA compliance from 92% to 99%.

Novartis

Hyderabad, IN

Technical Analyst Intern

Jan 2023 - Jul 2023

Engineered a NLP-driven clinical trial analysis workflow for drug-level sentiment mining, automated summarization, and outcome extraction from unstructured research documents, reducing manual literature review and evidence synthesis effort by 40% per quarter.
Built predictive and time-series forecasting pipelines on environmental operations data, integrating web-scraped external signals, feature engineering, and temporal trend analysis to support sustainability initiatives targeting a 19% annual reduction in carbon emissions.

Research Experience at Columbia University

Graduate School of Arts and Sciences

New York, NY

Machine Learning Engineer - Human Rights LLM Evaluation

Jan 2026 - Present

Developed a two-stage retrieval-augmented LLM framework with automated web search and chain-of-thought reasoning scoring 27 defense manufacturers across 9 human-rights dimensions, cutting analyst review effort by 80% with kappa and Krippendorff's alpha validation.

Lamont-Doherty Earth Observatory, McKinley Group

Palisades, NY

Data Scientist - Ocean Carbon Data Valuation

Sep 2026 - Present

Extending a Data Shapley framework valuing individual SOCAT surface ocean fCO_2 observations against a physical model prior rather than an empty baseline, using KNN-Shapley approximation and spatially blocked cross-validation to target where sparse, expensive measurements would most improve the ocean carbon sink reconstructions contributed annually to the Global Carbon Budget.

Irving Medical Center, AI4VS Lab

New York, NY

Computer Vision Engineer - Ophthalmic AI & Eye Tracking

Jul 2026 - Present

Developing gaze-augmented deep learning models for glaucoma diagnosis that fuse clinician eye-tracking with OCT report features, aligning model attention with expert reading behavior to make automated screening for irreversible vision loss auditable enough for clinical use.

Irving Medical Center

New York, NY

AI Engineer - Clinical LLM & Phenotyping

Jan 2026 - Present

Built an extraction system with hybrid de-identification, longitudinal EHR reconstruction, and hallucination-aware validation, converting unstructured notes into 56 cardiac sarcoidosis phenotype variables and replacing months of chart review with a manuscript-ready cohort.

Projects

Bank Complaint Refund Queue

github.com/rishika1099/Bank-Complaint-Refund-Queue | redress-five.vercel.app

A complaint queue for bank complaints teams: ranks CFPB complaints by how likely each is to end with money returned, explains every score, and writes an analyst brief with Claude.

NYC Rental Building Record Check

github.com/rishika1099/NYC-Rental-Building-Record-Check | before-you-sign-beta.vercel.app

Look up an NYC building's official housing record before signing a lease: violations, complaints, bedbugs and evictions from NYC Open Data, compared per apartment with similar buildings, summarized in plain English.

Email Campaign AB Test Readout

github.com/rishika1099/Email-Campaign-AB-Test-Readout

A product experiment readout on a real randomized email test of 64,000 customers: soundness checks, effects with intervals, who each email works for, and a decision.

⬇ download the PDF or open it as a page

Selected projects 🌱

6 of 104, the ones that argue for this role ✦

🎐

Bank Complaint Refund Queue

🏦 Finance

✨ Generative AI

A complaint queue for bank complaints teams: ranks CFPB complaints by how likely each is to end with money returned, explains every score, and writes an analyst brief with Claude.

⭑ Code ✿ Live demo

🗣️

NYC Rental Building Record Check

💬 NLP

Look up an NYC building's official housing record before signing a lease: violations, complaints, bedbugs and evictions from NYC Open Data, compared per apartment with similar buildings, summarized in plain English.

⭑ Code ✿ Live demo

🎙️

Email Campaign AB Test Readout

🌼 Machine Learning

A product experiment readout on a real randomized email test of 64,000 customers: soundness checks, effects with intervals, who each email works for, and a decision.

⭑ Code

🛣️

AI Intent Router Eval Kit

🌼 Machine Learning

A reusable harness and readiness report for deciding whether an intent router is safe to launch: in-scope accuracy, false accepts, wrongful declines and cost, at every setting.

⭑ Code

✋

Robot Demo Failure Triage

🌼 Machine Learning

Ranks real robot teleoperation episodes (DROID) by how likely each is a failed demonstration, from the arm's motion alone, so a reviewer watches the likely failures first.

⭑ Code ✿ Live demo

📚

DSI Course Evaluation

🎓 Education

✨ Generative AI💬 NLP

Student-built dashboard for Columbia MSDS course reviews, live Google-Sheets data, AI-summarized reviews, rankings, and side-by-side comparisons.

⭑ Code ✿ Live demo

all 104 projects →

Research 🔬

🏥

Jan 2026 – Present

Clinical LLM & Phenotyping

Columbia University, Irving Medical Center

Built a clinical information extraction system using an LLM pipeline to convert unstructured EHR notes into structured phenotype variables, ensuring patient privacy and accuracy for research readiness.

HealthcareGenerative AINLP

⚖️

Jan 2026 – Present

Human Rights LLM Evaluation

Columbia University, Graduate School of Arts and Sciences

Developed a two-stage retrieval-augmented LLM framework scoring defense manufacturers on human-rights due diligence, producing explainable assessments with preserved traceability and validating automated policy-risk assessment.

Human RightsLegalGenerative AI

🌊

Sep 2026 – Present

Ocean Carbon Data Valuation

Columbia Lamont-Doherty Earth Observatory (McKinley Group)

Extended a Data Shapley framework to score ocean measurements by their contribution to reconstruction accuracy, translating results into observing-system guidance for carbon sink measurements.

Machine LearningStatistical Modeling

👁️

Jul 2026 – Present

Ophthalmic AI & Eye Tracking

Columbia AI4VS Lab, Irving Medical Center

Developed gaze-augmented deep learning models for glaucoma diagnosis, aligning model attention with clinician visual search behaviour to enhance the interpretability of automated screening systems.

HealthcareComputer VisionDeep Learning

Experience 💼

Jun – Aug 2026

Predictive Analytics Intern

NYC Administration for Children's Services

Built a full explainability framework for a child welfare risk model, turning black-box predictions into transparent decisions through configurable operating thresholds and delivering an interactive dashboard for non-technical policy staff.

Public SectorHuman RightsMachine LearningPredictive Analysis

2023 – 2025

Software Engineer

Shell, Bengaluru

Built and deployed machine-learning forecasting pipelines in Databricks, enabling $100K+ in annual cost optimisation decisions and driving adoption across teams by turning operational questions into modelling problems.

Predictive AnalysisMachine Learning

Jan – Jul 2023

Technical Analyst Intern

Novartis, Hyderabad

Developed predictive and time-series forecasting models on supply chain and environmental operations data, supporting a Net-Zero initiative while automating a cross-reference task with an LLM-assisted workflow.

HealthcareNLPPredictive Analysis

📎 1 file inside

Feb – Mar 2022

Data Visualization Intern

Saint Louis University

Analysed Facebook ad campaign data to surface insights that informed targeting and strategy, delivering recommendations that improved campaign performance and ROI through interactive Tableau dashboards.

Statistical Modeling

📎 1 file inside

Education 🎓

2025 – present

Master of Science

Data Science

Columbia University, New York

Focus on machine learning and LLM systems, with coursework in applied deep learning and causal inference, and experience as a research assistant on LLM projects related to clinical phenotyping and human-rights evaluation.

2019 – 2023

Bachelor of Technology

Computer Science & Data Science

Vellore Institute of Technology (VIT)

Completed coursework in Artificial Intelligence, Machine Learning, and Predictive Analytics, graduating with a 4.0 GPA and ranked in the top 4% of the class.

Teaching 🍎

💬

Fall 2026

Natural Language Processing

Teaching Assistant, COMS 4705

Columbia University, Computer Science, taught by John Hewitt

From tokenization and transformers through RLHF, agents and interpretability.

NLPGenerative AIDeep Learning

🏛️

Spring 2026

Artificial Intelligence for Public Policy

Teaching Assistant

Columbia University, School of International and Public Affairs (SIPA)

AI fundamentals for policy students, and how to turn a policy problem into an AI solution.

Public SectorMachine Learning

Skills 🛠️

Product discoveryJobs to be doneSuccess metricsExperiment designA/B testingDecision memosLaunch readinessCompetitive analysisResponsible AILLM productsEvaluationPythonSQL