Akhil Vinayak P

Summary

Data Science professional with experience delivering end-to-end ML solutions, scalable data pipelines, and cloud-native workflows using Google Cloud Platform. Skilled in Python, BigQuery, PySpark, model development and evaluation, and translating business requirements into data-driven products.

Professional Experience

Senior System Engineer – Infosys, Trivandrum, Kerala (Jan 2023 – Present)

• Analyzed large-scale telecom datasets to optimize operations and support decision-making.
• Developed ML models like KMeans and XGBoost with SHAP-based explainability and cluster profiling.
• Built scalable data pipelines reducing preparation time by 20% and integrated multi-domain data sources.
• Used GCP (Vertex AI, DataPlex, BigQuery, PySpark) to deliver production-grade AI workflows.
• Explored integration of Generative AI techniques for innovative system enhancements.

Junior Python Developer – Turbolab Technologies, Kochi, Kerala (Jul 2021 – Aug 2022)

• Built and maintained ETL pipelines for web data extraction using Python.
• Improved data quality with validation checks using Pandas and custom tools.
• Designed modular, reusable Python codebases to adapt to changing website structures.
• Ensured system reliability through continuous monitoring and stress-tested API deployment.

Skills

• Data Science & ML: Statistics, Predictive Modeling (Classification & Regression), Scikit-learn, XGBoost, SHAP
• Programming: Python, SQL
• Cloud Platforms: Google Cloud Platform (Vertex AI)
• MLOps: Vertex AI Pipelines, MLflow, Kubeflow, Docker
• Data Analysis & Viz: Pandas, Seaborn, Matplotlib, Kibana
• Big Data: BigQuery, Dataform, GCS, PySpark, Airflow, HDFS
• Version Control: Git, GitHub, Bitbucket
• Data Governance: DataPlex, Data Catalog, Quality Monitoring
• GenAI: NLP, LLMs, RAG, Agents, Prompt Engineering (LangChain, LangGraph)
• Project Management: JIRA, Confluence

Education

• Central University of Kerala (2019 – 2021): Master of Computer Science (Intelligent Systems), CGPA: 8.39
• Mahatma Gandhi College (2016 – 2019): Bachelor of Computer Science, CGPA: 8.5

Projects

Virtual Realtor (Nov 2024 – Present)

• Built a virtual home finder app using web scraping, predictive analytics, and LLMs.
• Created real-time data pipelines for home listings and locality insights.
• Developed ML model to predict home prices with contextual explanations.
• Used LLMs for feature extraction from unstructured listings.
• Implemented RAG to support natural language search by home features.
• Tech Stack: Python, Airflow, Kubeflow, MongoDB, LangChain, DeepSeek, ChromaDB, Kibana

Certifications

• DeepLearning.AI TensorFlow Developer Specialization – Coursera (2020)
• Machine Learning Specialization – University of Washington via Coursera (2020)