Agentic AI · Data Engineering
Agentic workflows, RAG pipelines, and the backend plumbing behind them — delivered end to end for enterprise finance clients.
About
I'm Jalaj Trivedi, a Forward Deployed Engineer at Peakflo. I own AI proof-of-concepts end to end for enterprise finance clients — gathering requirements with stakeholders, designing the solution, building it, and taking it to production.
Before this I architected an AI-powered Fraud Risk Management platform for banking institutions, onboarding City Union Bank as the first enterprise client. I studied Data Science at IIT Madras and Computer Science Engineering at Indus University.
Selected work
IIT Madras · MLOps · Kubernetes
Deployed a production-ready Heart Disease Prediction API on Google Kubernetes Engine (GKE) using Docker and FastAPI. Configured HorizontalPodAutoscaler (HPA) for load management and implemented comprehensive observability via Google Cloud Logging. Integrated SHAP for model explainability and performed fairness analysis (Fairlearn) to detect gender bias.
View on GitHub→Kaggle Competition · Machine Learning
Participated in Kaggle's Crime-Cast competition as part of an IIT Madras project, building and optimizing machine learning models using Python, scikit-learn, and XGBoost to predict crime categories. Applied feature engineering, data preprocessing, and visualized insights using Seaborn and Matplotlib.
View on GitHub→Full-Stack Build · Web Application
Developed a comprehensive web application featuring Role-Based Access Control (RBAC) for librarians and users, built with Flask, Vue.js, and SQLite. Implemented Redis caching for performance optimization and utilized Celery for asynchronous background jobs, such as daily reminders and monthly activity reports.
View on GitHub→Research Project · Deep Learning
Built an image captioning system leveraging a CNN-LSTM architecture with VGG-16 for image encoding. Improved performance with Batch Normalization and Dropout techniques and evaluated results using BLEU scores. Developed and trained the model using TensorFlow/Keras.
Expertise
Hobbies
I love to travel and explore new places, play outdoor sports, and stay connected to spirituality. The mountains keep me grounded — and give me stories for Monday.
Travel & explore
Road trips, mountain villages, and the long way there.
Outdoor sports
Trekking, high-altitude trails, and time outdoors.
Spirituality
Quiet moments in the mountains — presence, gratitude, and perspective.
Wanderlust
Sunny villages, prayer flags, and open skies.
Contact
Have a role, a project, or an AI problem worth solving? Send a message — or reach me directly.
