Open to opportunities

Radhika Gujral

@radhikagujral

Message

Data Scientist with 1.5+ years building ML, RAG, and analytics automation for real-world decisions.

Zimbabwe

Message

What I'm looking for

I’m looking for a role where I can build end-to-end ML and analytics products—productionizing models with strong MLOps, scalable data pipelines, and close collaboration with business stakeholders.

I’m a Data Scientist with 1.5+ years of experience building machine learning solutions, analytics platforms, automation frameworks, and data products across financial services and analytics domains. I work end-to-end across the ML lifecycle—feature engineering, model evaluation, deployment, monitoring, and scalable data pipelines.

At Goldman Sachs, I built a Python-based SQL query generation framework using prompt engineering and language-model translation, reducing analyst query development effort by 70%. I also delivered a semantic search layer over internal treasury documentation, automated treasury reporting/reconciliation workflows (reducing manual effort by 60%), and optimized complex SQL workloads to improve reporting turnaround time by 40%.

My project work includes a RAG-based Treasury Policy Q&A Assistant using LangChain, FAISS, and Sentence Transformers, cutting incorrect/unsupported answers by ~30% in testing while adding source citations for auditability. I’m energized by turning business requirements into reliable, production-ready data and AI systems with strong MLOps practices.

Experience

Work history, roles, and key accomplishments

Current

Data Scientist

Current

Goldman Sachs

Jan 2025 - Present (1 year 6 months)

Designed a Python-based SQL query generation framework using prompt engineering to translate business requirements into optimized SQL, reducing analyst query development effort by 70%. Built a semantic search layer over internal treasury documentation and automated treasury reporting and reconciliation workflows, reducing manual effort by 60%.

Python SQL Prompt Engineering Language Models Semantic Search Snowflake Alteryx ETL Data Pipelines Predictive Analytics Pandas NumPy scikit learn XGBoost Matplotlib Scipy SQL Query Optimization

Data Science Intern

Voiceback Analytics

Jun 2024 - Jul 2024 (1 month)

Built sales forecasting models using historical retail data to predict demand across multiple locations. Developed automated analytics dashboards and visualization pipelines, and performed feature engineering, model evaluation, and hyperparameter optimization to improve forecasting accuracy.

Sales Forecasting Forecast Modelling Feature Engineering Model Evaluation Data Visualization Dashboarding Data Pipelines

Backend & Data Eng Intern

Unnati Agritech

Jun 2023 - Aug 2023 (2 months)

Developed and integrated new features into an existing application, improving location alignment accuracy and system reliability using Django, Docker, CSS, and JavaScript. Improved data processing performance and reliability through workflow optimization and database tuning.

Django Docker CSS JavaScript Workflow Optimization