Kinshuk Das

Data Engineer with 6+years of experience in building scalable data solutions and platforms. Proven experience in data modelling, designing architecture. Strong background in Python, cloud data services, and orchestration tools. Adept at leading teams, delivering high-impact projects, and aligning data infrastructure with business goals.

Languages: Python, SQL, Cypher Query Language (CQL), GraphQL.

Databases: Neo4j, PostgreSQL, MongoDB, Redis.

Frameworks & Libraries: FastAPI, Dagster, Dash, Streamlit, Plotly.

Cloud Platforms: Redhat Openshift, Azure.

Orchestration: Docker, Kubernetes

Others: Git, Jupyter, Jenkins, Azure Pipelines.

Predictive Maintenance of Rolling Chassis (Jan 2025 – Present)

• Worked with stakeholders to identify the required information for analysis.
• Defined the data exchange process and how sensor data will be extracted.
• Designed the initial architecture and developed a proof of concept (PoC) to evaluate latency.
• Deployed services in the cloud and conducted tests with sample data.
• Tech Stack – Python, Redis, MQTT, Azure function, Docker.

Signal Dependency Network (Apr 2021 – Present)

• Working as an architect in the project to design the software architecture, defining different micro services.
• Understand the TCU software components and modelling the knowledge graph.
• Getting insights from the knowledge graph, for example finding the shortest path between signals.
• Developed the ETL workflow which integrate the static code analysis tool Astree which analyzes the source code and provided the report which is then used to create the Knowledge Graph.
• Setting up CI/CD workflows for testing and deployment to ensure the quality.
• Tech Stack – Python, Neo4j, FastAPI, Celery, Redis, Docker, Openshift

Computer Vision and AI for Quality Inspection (Jan 2024 – Jul 2024)

• Developed a system for the engineers in the plant to identify the faulty components where Engineers need to upload a picture and the system can check whether the component is faulty or not in real-time using Machine Learning.
• Analyzed raw images, doing basic image preprocessing (resizing, normalization etc)
• Used transfer learning to train the pre-trained models on the available images.
• To improve the accuracy we have used background removal and extracted regions of interest and trained the model again.
• Deployed services in the cloud and conducted tests with sample data.
• Tech Stack – Python, OpenCV, Pytorch.

Product Data Knowledge Graph (Jan 2020 – Aug 2022)

• Worked as a data engineer, responsible for gathering information about different data sources and fetching raw data.
• Analyzing the data to understand the possible connections.
• Ingest data into the Graph database to create the knowledge graph.
• Developed micro-services which enables fetching data from the graph for further analytics.
• Setup CI/CD workflows to test and deploy the services.
• Tech Stack – Python, Dagster, GraphQL, Neo4j

Machine Learning for Live Application Monitoring (Aug 2018 – Jul 2019)

• Developed a dashboard which updates on real-time to give insights on the user feedbacks for the personal healthcare products, it uses Machine Learning to analyze user reviews.
• Gathered raw data (user reviews and ratings) for the mobile applications.
• Analyzed the data and used NLP to extract useful features.
• Used supervised and unsupervised machine learning algorithms to do the classification then topic modeling.
• Automated the whole workflow which enabled fetching and processing data in real-time.
• Developed an interactive dashboard which helped the developers to understand the key areas of improvement.
• Tech Stack – Python, PostgreSQL, Spacy, scikit-learn, Plotly, Dash.

Neo4j Certified Professional