Diksha .

Founder

Sweden6 yrs 5 mos experience

Highly Stable

Key Highlights

Hands-on experience in data pipelines and machine learning.
Developed a data quality framework for government projects.
Proficient in Python and AWS for data-driven solutions.

Stackforce AI infers this person is a Data Science professional with a focus on government projects and machine learning applications.

Contact

Skills

Core Skills

Data ScienceMachine Learning

Other Skills

AWSAirflowAnalyticsBusiness InsightsCNNConvolutional Neural Networks (CNN)DashboardsData AnalysisData PipelinesData QualityData VisualizationDeep LearningHadoopLeadershipMapReduce

About

Currently pursuing a Master’s in Data Science at Dalarna University, with a focus on practical applications and data-driven solutions. Academic endeavors are complemented by hands-on experience in data pipelines, data quality frameworks, and deep-learning model training for government projects during a Data Science internship at Unicloud. Proficient in Python and experienced in leveraging tools like Airflow and AWS for data movement and validation. Motivated to contribute to meaningful projects that utilize data science to solve real-world challenges, with goals to deepen expertise in data pipelines, analytics, and machine learning.

Experience

6 yrs 5 mos

Total Experience

3 yrs 4 mos

Average Tenure

Current Experience

Unicloud

2 roles

Data Science Intern

Promoted

Jul 2025 – Sep 2025 · 2 mos · Hybrid

Common Data Repository (CDR) to train deep-learning models for various departments under Ministry of Rural Development (MORD). I gained hands on experience on following project activities:
Data Pipelines: MORD manages multiple government schemes to support rural India population. Each scheme has its own database of beneficiary & system of records (SOR). Project involved creating Data pipelines on Airflow to move Data from source systems to S3 on AWS and stored in Parquet/CSV formats as Bronze layer.
Data Quality Framework: A Data-Quality framework was developed using Python that executed custom validation functions during data movement in the pipeline and store validated records as Silver layer. Further, business transformation were written in Py-Spark to generate Gold layer.
Machine Learning Model Training: Gold layer was made available via Aws Athena & Glue tables for exploratory data analysis. While machine learning model training was implemented using Sage-maker container service within Python notebook. For few schemes where data size was very large, Data parallelism was implemented using distributed model training in PyTorch.

Data PipelinesData QualityMachine LearningPythonAWSAirflow+3