Saurabh Kamboj

Chunkwise is an open-source, self-managed platform for evaluating chunking strategies and deploying ETL pipelines for RAG applications. It supports experimentation with visualization and corpus-specific benchmarking, alongside deployment of document processing pipelines within a single cohesive system. I implemented a distributed backend that isolates compute-intensive chunking and evaluation into containerized services, coordinated through a RESTful orchestration API with shared Pydantic models. The system integrates token-level chunking evaluation by adapting Chroma’s metrics framework with reusable, LLM-generated ground-truth references. I designed and built the client interface for experimentation and deployment workflows, supporting real-time visualization optimised using debouncing, trackable deployment state via Server-Sent Events, local caching of reusable metadata, and runtime request and response validation. In parallel, I prototyped the ETL pipeline, handling RDS provisioning, secrets management, and S3 ingestion with real-time deployment state streaming and secure, local-only credential retrieval using ARNs. The ETL pipeline was later scaled using AWS Batch on Fargate to parallelize document chunking and embedding generation while actively managing external API rate limits to prevent throttling. I also implemented client- and server-side encryption of S3 credentials using ephemeral, in-memory RSA key pairs, preventing plaintext transmission in a non-TLS, locally run client setup.

Developed open-source software across multiple application domains. Built Request Bin, a developer tool for receiving, persisting, and inspecting HTTP requests in real time via generated URL endpoints (JavaScript, Node.js, Express, React, WebSockets, AWS). Also built a wine-review chatbot, a chat loop using structured outputs and RAG to enable semantic and keyword-based wine search and recommendations over a 130k-review dataset (Python, PostgreSQL, pgvector, OpenAI API, Mem0 API), as well as a message board (forum) with a simple relational database design (Ruby, Sinatra, PostgreSQL).

Led cross-functional development of digital commerce stores for early-stage brands with ARR up to $5M, collaborating with designers, developers, and quality analysts. Built internal tools for ads reporting (using Facebook’s Graph API), billing, and revenue, and tracked sales performance to inform ongoing optimization and scaling efforts.

Designed and built a health information platform combining a storefront and learning management system to distribute micro-courses authored by health professionals. Collaborated with a fully remote team distributed across Nepal, India, Brazil, and Germany. Created both educational resources and medical illustrations covering 17 health topics. Maintained an average of 62+ weekly active users over five months and acquired 30+ paying customers. Completed the Startup School program and applied to Y Combinator, where the company was selected for interview.

Led a multidisciplinary team of designers, developers, and marketers to build and manage digital platforms, landing pages, and marketing campaigns for a global non-profit operating across more than 30 cities in India. Built internal tools to support operations, including cost calculators, lead planners, and progress trackers, and led the integration of digital payments and digital contracts. Implemented GDPR compliance for India across national digital platforms. Drove growth in key operational KPIs across two focus products, and received an internal global award.

Led and executed multi-channel marketing campaigns. Planned and ran the organization’s first paid marketing initiative, coordinating a live call center, managing up to ₹8 lakh in digital ad spend over a two-week period, and delivering multiple conversion-optimized landing pages to support campaign performance.