Open to opportunities

Harshita Rani

@harshitarani

Message

Software engineering intern building NLP risk models and machine learning systems.

India

Message

What I'm looking for

I want a role where I can build production-ready ML/NLP pipelines, ship models that improve accuracy, and keep learning—especially in projects involving risk prediction, text understanding, and computer vision.

I’m a Software Engineering Intern focused on turning real-world data into reliable AI. I build end-to-end pipelines and models, from NLP semantic search to predictive risk modeling and research-driven generative workflows.

In my current role, I engineered an automated Python data pipeline processing SEC filings and CRSP market data for 28,700+ companies. I reduced preprocessing time by 80% while extracting 93,000+ risk exposures, and I improved volatility prediction accuracy by 15% using Random Forest and OLS on a 93,000+ record dataset.

I also enjoy exploring new directions—developing diffusion/CV workflows that reduce manual product photography effort by 60%, building DeepFake detection with CNNs (87% validation accuracy), and delivering sentiment classification (86.3% accuracy) for finance news. Alongside ML, I’ve built SQL/MySQL systems with triggers and functions, and I keep strengthening my foundation through certifications and active tech exploration.

Experience

Work history, roles, and key accomplishments

Current

Software Engineering Intern

Current

Emergeflow Technologies

Jan 2026 - Present (5 months)

Engineered a Python NLP pipeline to process SEC filings and CRSP market data for 28,700+ companies, extracting 93,000+ risk exposures and reducing preprocessing time by 80%. Built ML models on a 93,000+ record dataset to improve volatility prediction accuracy by 15% and explored diffusion/CV workflows to cut manual product photography effort by 60%.