MLOPS Engineer

Machine Learning Operations Engineering for Cybersecurity Platform of GOI Client.

• Developed and deployed data and machine learning solutions for ML-based threat detection.

• Collaborated closely with clients to understand their requirements regarding to data, cyber attacks, POCs, etc.

• Performed threat modeling for HTTP Layer cyber attack during a collaborative R&D activity, and thus generated

realistic attack data for ML Modelling. Successively developed statistical ML model for effective detection.

Authored whitepapers, presentations to communicate work/findings to clients.

• Developed end-to-end ML-based threat detection pipelines utilizing Airflow, MLflow, Docker, SKlearn, Postgres,

Neo4j etc. in Linux-based environments for use-cases like Lateral Movement, DoS, etc. detection.

• Developed and containerized components of ML prediction pipelines using Docker, & integrated them in Airflow DAG

scripts utilizing dockeroperator, thus making 5+ pipelines operational.

• Co-created ETL framework in collaboration with module leads to capture & store Network Traffic in Data Lake

(elastic search). Ensured the uptime of ETL processes using continuous process monitoring & cron job.

• Built containerized data processing libraries for packet captures, integrated them with ETL Framework to make data for

use-case available on Data Lake(elastic search), thus solved data availabilty issue for use-cases.

• Deployed MLflow in on-premise cloud using docker-compose with Nginx as reverse proxy and FTP as a backend. Led &

guided its integration in 10+ pipelines on Airflow. Provided support to developers to ensure seamless mlflow

operations and model lifecycle management.

• Design and implemented scripts to automate deployments of Airflow DAGs, Docker setups, etc. using

Python,Bash,Make, slashing deployment times, streamlining workflows, and minimizing manual effort.

• Consistently recognized for exceptional collaboration and component integration skills.

• Tech Stack: Python, Numpy, Pandas, Sklearn, SQL (Programming & ML); Airflow, Mlflow, Docker, Elastic Search,

Postgres, Linux Tools, GIT (MLOps/Data Toolkit); Scapy for network programming, Tcpdump (Cybersecurity)