Amritesh Tiwari

Data Analyst & Analytics Engineer with 1.5+ years of experience leveraging Python, SQL, and AWS cloud workflows for renewable energy modeling and quantitative analysis. Proven track record in model validation, pipeline automation using Dask and Jenkins, and building BI dashboards in Apache Superset. Skilled at transforming complex assets, power generation, and weather datasets into automated, scalable analytical pipelines.

Data Associate at WOOD MACKENZIE (2025-05 – Present)

• Developed and validated solar and wind energy-yield modelling workflows, working with asset, weather and generation data across multiple renewable-energy markets.
• Built Python, SQL and Dask-based analytical workflows for data transformation, model-output comparison and quantitative error analysis.
• Developed Apache Superset validation dashboards and SQL datasets on AWS, enabling repeatable analysis of model performance and data quality.
• Investigated data and model-quality issues involving generation, capacity, weather inputs and model outputs, translating findings into fixes and validation improvements.
• Improved recurring modelling workflows using Jenkins and AWS Step Functions, reducing pipeline startup time from approximately 8.5 minutes to 2 minutes.
• Executed and validated quarterly production model runs, including input preparation, automated testing, troubleshooting and output validation across cloud environments.

Project Intern at TATA CONSULTANCY SERVICES (TCS) (2024-01 – 2024-07)

• Designed and tested Pywinauto-based Python automation scripts, accelerating 50+ workflows by 20% and saving 10+ manual engineering hours weekly.
• Partnered with a 10-member cross-functional team to gather technical requirements and deliver process documentation, reducing team onboarding time by 15%.

Software Developer Intern at QUANTBIT TECHNOLOGIES LTD (2023-11 – 2024-01)

• Built machine learning-powered image analysis tools using Python and TensorFlow, achieving 95% classification accuracy on test datasets.
• Processed and structured 10,000+ data points for feature extraction, improving real-time model processing performance by 25%.

B. Tech in Computer Science and Engineering – Annasaheb Dange College of Engineering and Technology, Sangli (2020-08 – 2024-06)