Open to opportunities

Sahil Sainath Shirodkar

@sahilsainathshirodka

Message

I build production-ready RAG, LLM, and machine learning systems backed by enterprise software engineering experience.

India

Message

What I'm looking for

I'm seeking Machine Learning Engineer, GenAI Engineer, or Applied AI Engineer roles where I can ship end-to-end AI systems using RAG, LLM orchestration, and applied ML with production engineering discipline.

I've built a multi-document RAG system for context-aware querying across PDF, DOCX, and TXT files using FastAPI, LangChain, FAISS, LLMs, AWS, and LangSmith evaluation.

At Open Destinations Ltd, I develop enterprise travel applications with ASP.NET Core, C#, MySQL, and AngularJS. I reduced backend processing time from 10 minutes to under one second, cut issue-resolution time by 40%, and reduced application downtime by 25%.

My applied ML projects include a fraud detection system achieving 0.98 ROC-AUC and 0.96 Gini coefficient, plus a health insurance premium predictor with an R² of 0.98. I've handled preprocessing, feature engineering, model evaluation, hyperparameter tuning, and Streamlit deployment.

I've also built pricing recommendation models using Logistic Regression, SVM, Random Forest, and XGBoost, achieving 92.19% accuracy with XGBoost. I bring production debugging, deployment discipline, and cross-functional delivery experience to end-to-end AI/ML systems.

Experience

Work history, roles, and key accomplishments

Current

Senior Software Developer

Current

Open Destinations Ltd

Feb 2023 - Present (3 years 6 months)

Developed and maintained enterprise travel applications using ASP.NET Core, C#, MySQL, and AngularJS. Optimized backend business logic, reducing processing time by 99.8% and cutting resolution time by 40%.

ASP.NET Core C#MySQL AngularJS Debugging Performance Optimization Cross Functional Collaboration

Data Science & Machine Learning Intern

Codebasics Virtual Internship

Feb 2026 - Apr 2026 (2 months)

Performed exploratory data analysis on retail campaign data across 50 stores and built an end-to-end ML pricing recommendation system using 30,000 customer records. Trained and evaluated multiple models, achieving 92.19% accuracy with XGBoost.