Open to opportunities

Ripu Sudan

@ripusudan

Message

Generative AI Technical Lead building scalable backend systems and RAG-powered automation for enterprise teams.

India

Message

What I'm looking for

I’m looking to lead end-to-end Generative AI and backend system design—building RAG/LLM solutions, optimizing cost and latency, and scaling distributed microservices with strong team execution and cross-functional collaboration.

I’m a Technical Lead with 10+ years of experience building and scaling distributed systems and AI-driven platforms, with a strong focus on Generative AI and backend architecture.

For the past 2+ years, I’ve driven end-to-end Generative AI initiatives—building RAG pipelines, integrating LLMs, and delivering intelligent automation systems that work in real production environments.

I lead teams of engineers across AI, backend, and frontend, and I build solutions that reduce cost and improve user experience. In my current role, I optimized LLM usage through caching, prompt design, and workflow improvements—cutting inference costs by 30% and improving response latency by 50%.

I’m equally focused on system reliability and scale: I architect scalable backend services for high-throughput AI workloads and real-time interactions, set engineering best practices that improve productivity (reducing delivery cycle time by 30%), and partner with cross-functional stakeholders to translate complex requirements into robust microservices.

Experience

Work history, roles, and key accomplishments

Current

Technical Lead (Generative AI)

Current

Trantor Software Pvt. Ltd.

Jan 2024 - Present (2 years 4 months)

Led a team of 10 engineers to deliver enterprise Generative AI solutions, designing end-to-end RAG pipelines with vector search for document understanding and conversational AI. Reduced inference costs by 30% and improved response latency by 50% through caching, prompt design, and workflow optimization.

Generative AI Vector Search Prompt Engineering Microservices Architecture Caching Strategies AWS GCP Performance Optimization

Senior Application Development Engineer

ChargePoint Inc.

Jun 2023 - Jan 2024 (7 months)

Developed and maintained software systems for EV charging hardware platforms and contributed to backend services for device communication and monitoring. Supported factory-level system initialization and burn-in testing to ensure production readiness and reliability.

Backend Services System Integration Monitoring Reliability Engineering Hardware Software Integration Factory Testing Burn In

Technical Lead - OneApp

Quickgov Solutions Pvt. Ltd.

Aug 2021 - Jun 2023 (1 year 10 months)

Led backend development and system architecture for a platform used by police departments and courts across ~30 cities. Built scalable Python (Django) microservices and mission-critical REST APIs, improving reliability and performance through optimized database queries, caching, and service design.

backend architecture Python Django Microservices Architecture REST APIs Caching Stakeholder Management Systems Performance

Software Engineer

Trantor Software Pvt. Ltd.

Dec 2019 - Aug 2021 (1 year 8 months)

Collaborated with ML teams to deploy production-ready models using Python and JavaScript, handling backend integration and server-side deployment. Delivered an end-to-end IoT proof-of-concept by defining architecture, guiding implementation, and meeting client requirements.

Python JavaScript Backend Integrations API Design Server Side Deployment System Architecture

Software Engineer

Sapieo Software LLC & Mannan Impex

Dec 2016 - Dec 2019 (3 years)

Contributed to Django backend systems for Honda’s loyalty and recommendation platform. Built backend services for an IoT smart home platform, implementing multi-room synchronization and device-control APIs for real-time mobile interactions.

Django IoT Platform Multi Room Synchronization Recommendation Systems REST APIs Real Time Device Interactions Java React