About
Soumee Mukherjee
ML Researcher · Software Developer
ML researcher and software developer working across retrieval-augmented generation, information trustworthiness, multi-agent behaviour, and computer vision. Her work combines production engineering with published research in deep learning and complex systems modelling.
Delhi, India
Experience
Dec 2023 - Present
Delhi, India
Software Developer
Cabinet Secretariat, Government of India
Builds production information-retrieval, public-source analysis, and geospatial visualization capabilities.
- Develops retrieval-augmented document analysis with source-grounded outputs.
- Builds multilingual public-source aggregation and analysis workflows.
- Creates configurable geospatial tools for interactive maps and visual reports.
Skills:- Python
- Information Retrieval
- RAG
- Data Pipelines
- Geospatial Visualization
Nov 2023 - Dec 2023
Kolkata, India
Internship Trainee
Calcutta Electric Supply Corporation
Worked with the Security Operations Centre supporting critical network monitoring and process automation.
- Supported Internet leased-line monitoring for metropolitan power distribution infrastructure.
- Automated operational processes on the Zabbix monitoring server.
Skills:- Network Security
- Zabbix
- Palo Alto Firewall
- PuTTY
Education and fellowship
Aug 2019 - Aug 2023
B.Tech in Computer Science and Engineering
Heritage Institute of Technology
Kolkata, India · GPA: 9.12/10
Selected coursework: Probability and Statistics, Data Science, Natural Language Processing, Pattern Recognition, Numerical Methods, Relational Databases, NoSQL Databases
Jan 2023 - Mar 2023
Winter Workshop on Advanced Machine Learning
Indian Statistical Institute
Kolkata, India
Jul 2022 - Oct 2022
MITACS Globalink Research Internship
University of Calgary
Selected for a funded research internship from a global pool of 20,000 applicants.
Technical skills
Programming
Python · Java · C · C++ · Shell · SQL · LaTeX
AI, NLP, and RAG
PyTorch · TensorFlow · Hugging Face · scikit-learn · LLMs · Retrieval-Augmented Generation · Encoder-Decoder Architectures · Pandas
Computer Vision
OpenCV · MediaPipe · U-Net · Image Segmentation
Data and Search
Elasticsearch · NumPy · MySQL · PostgreSQL · MongoDB
Simulation and Geospatial
NetLogo · Folium · Leaflet · Geopy
Infrastructure and Tools
Docker · Playwright · Linux · SLURM · Git · REST APIs
Web
HTML · CSS · JavaScript · Streamlit