Data Scientist

Mohamed Arif Nather S A

§ Github ï LinkedIn Portfolio # *******************@*****.*** H +91-638******* Summary

Highly motivated Data Science and Analytics professional with proven expertise in Python, Machine Learning, Deep Learning, NLP, LLMs, Generative AI, Power BI, and Data Visualization. Experienced in transforming raw data into actionable business insights, building predictive AI models, and delivering real-time analytical dashboards. Certified in Python by Bharathidasan University and recognized for innovation, leadership, and high-impact projects. Passionate about solving real-world problems using data-driven decision-making, AI-powered automation, and advanced analytics. Continuously upgrading expertise in LLMs, NLP, Generative AI, and AI agents to deliver scalable, high-impact solutions. Work Experience

Shiash Info Solutions Private Limited Sep 2024 - June 2025 Data Science Intern

– Learned and applied core concepts of statistics, ML and DL through theoretical study and real-world projects; self-taught Power BI for business intelligence.

– Constructed a RAG pipeline (LangChain loaders chunking HuggingFace embeddings Chroma) and integrated Groq LLM for contextualized knowledge retrieval; deployed via Streamlit.

– Built AI content agents (planner writer editor) using Crew AI + Serper Dev for up-to-date article generation; implemented editorial checks and formatting automation.

– Developed and tuned non-linear ML models (Polynomial Regression, SVR) and DNNs (ReLU, tanh activations) on Chennai property tax datasets to improve prediction performance.

– Built production-style pipelines for web scraping, data cleaning, and dataset creation (BeautifulSoup, pandas) to enable downstream analytics.

– Expanded expertise in LLMs, NLP, Generative AI, AI agents, and advanced data engineering techniques. Projects

AI Content Generation Agent Link to Demo

Implemented multi-agent AI pipeline with Crew AI to research, write, and edit articles using up-to-date web data.

RAG Application for Knowledge Management Link to Demo Integrated LangChain loaders, HuggingFace embeddings, Chroma DB, and Groq LLMs in a Streamlit UI for interactive document and video search.

Chennai Property Tax Prediction (ML) Link to Demo

Built and tuned non-linear regression models with cross-validation and hyperparameter optimization for improved accuracy. (Python, scikit-learn)

Chennai Property Tax (DL) Link to Demo

Designed multi-layer DNN with ReLU and tanh activations, tuned hyperparameters to minimize loss and improve generalization. (TensorFlow/Keras)

Chennai Urban Heat Risk Analysis Link to Demo

Used Google Earth Engine to map Urban Heat Island hotspots using LST, NDVI, nighttime lights, and population data. (GEE, Remote Sensing)

View more projects

Achivements and Highlights

– Awarded A++ grade for departmental research project recognized for innovation and data-driven insights.

– Head Member — Paper Presentation Committee (led event coordination and team management).

– Python certification from Bharathidasan University.

– Workshops at NIT Trichy and St. Joseph’s College; active in AI and analytics webinars. Skills

Programming and Querying Python, SQL.

Machine Learning and Deep Learning scikit-learn (Polynomial Features, SVR, GridSearchCV), TensorFlow / Keras, PyTorch, model tuning, cross-

validation, feature engineering, neural network design

(ReLU, tanh).

NLP, LLMs, RAG LangChain, HuggingFace embeddings and Transformers, Groq LLM integration, Retrieval-Augmented Generation

(RAG), prompt engineering, Chroma vector DB, document and audio loaders, transcription pipelines.

Data Handling and Visualization pandas, NumPy, Matplotlib, Seaborn, Power BI, Excel

(Pivot, Power Query), Streamlit (UI).

Web and Automation Jupyter Notebook, Power BI, Excel, Git, VS Code, Google Colab.

Geospatial and Remote Sensing Google Earth Engine, LST (Land Surface Temperature), NDVI, urban masking, raster analysis, GIS fundamentals. Dev and Ops / Productivity Git, Jupyter Notebook, VS Code, CSV / Parquet, API in- tegration.

Soft / Business Skills Data storytelling, KPI definition, stakeholder communica- tion, problem framing, cross-functional collaboration, ex- perimental rigor.

Education

2021 - 2024 Bachelor’s Degree at Jamal Mohamed College (CGPA: 8.6) 2020 - 2021 Class 12th at Golden Gates Matric Hr Sec School (Percentage: 80.5) 2018 - 2019 Class 10th at Golden Gates Matric Hr Sec School (Percentage: 68.2) Language

English

Tamil

Contact this candidate