I am Sarvesh Patil,
an AI Engineer
& Full Stack
Developer.

• Stepping into a senior role with a focus on designing and delivering more complex AI-driven systems across data workflows and enterprise applications.

Pitchbook Generator

• Led a 6-member team to automate 80% of investment pitchbook creation by engineering an AI-driven system using LangChain agents, reducing manual effort and enabling real-time updates via natural language.
• Accelerated banker workflows by 3x by building AI modules for executive summaries, benchmarking, stock comparisons, and dynamic world maps, fully integrated into Nomura's internal ecosystem.
• Reduced turnaround time and improved consistency across 100+ pitchbooks annually by building an Assembly Engine that merged AI-generated content into Nomura's standard PowerPoint templates.
• Stack: Langchain Agents, LLMs, FastAPI, Next.js, Python, Matplotlib, Geopy, Pillow, Tailwind CSS

Backstage - Internal Developer Portal

• Reduced release analysis time from hours to seconds and improved incident response by implementing AI-powered ETL systems that automated data ingestion, analysis, and summarization, delivering real-time insights, root-cause and trend analyses across 500+ applications to enable faster detection and decision-making for tech teams & management.
• Unified CI/CD visibility across 500+ repositories by integrating GitLab CI and Jenkins into a centralized Backstage plugin, boosting GitLab CI adoption by 25% and streamlining migration from Jenkins to GitLab CI.
• Improved governance hygiene by developing a Backstage plugin that visualizes real-time metrics (incidents, changes, infringements, configurations), reducing dependence on manual reporting for 120+ application teams.
• Stack: LLMs, FastAPI, Python, Backstage, React.js, Node.js, GraphQL, MongoDB, Typescript, MUI

• Accomplished digitalization of the toilet community data collection process by developing a full-stack MERN web portal and admin dashboard which led to streamlined data management and elimination of paper-based workflows.
• Reduced server storage costs by 50% by implementing an image compression pipeline, lowering operational expenses.
• Ensured secure and efficient data handling by integrating OTP-based auth, PDF/Excel exports, and EC2 deployment.
• Stack: Next.js, Node.js, Express.js, MongoDB, Amazon EC2, Sharp, 2Factor, JSPDF, XLSX, Tailwind CSS

• Delivered seamless 3D model search and purchase by integrating Sketchfab and Poly-Pizza APIs with a Razorpay payment gateway, improving user workflow and platform usability.
• Strengthened authentication security by implementing Passport.js and bcrypt-based encryption in MongoDB, enhancing data protection and reducing security risks.
• Improved user workflow efficiency by architecting the Mongoose schema and building the Login, Register, and Courses pages in React.js/TailwindCSS, reducing latency and enabling smoother interactions.
• Stack: React.js, Node.js, Express.js, MongoDB, Passport.js, Razorpay, Tailwind CSS

• Improved policy accuracy by implementing validation logic, reducing manual errors.
• Enhanced release stability by testing and managing/merging code, cutting deployment issues.
• Enabled efficient data sharing by adding PDF dashboard downloads, boosting reporting efficiency.
• Achieved clearer product direction by designing Figma wireframes and prototypes, reducing development rework.
• Stack: Python, Flask, Figma, Git

• CGPA: 9.89/10 (Department Rank 1)
• Honors Degree in Artificial Intelligence & Machine Learning
• Recipient of Narotam Sekhsaria Foundation Scholarship for academic merit