Architecting Order from Chaos | Designing for
Possibilities & Adaptability
Automation Engineer & Systems Architect — crafting agentic RPA pipelines, distributed infrastructure, and production-grade LLM integrations that scale.
About Me

Automation Engineer and Systems Architect specializing in agentic RPA pipelines, distributed infrastructure orchestration, and production-grade LLM integration. I operate at the intersection of intelligent automation, DevOps, and scalable systems design.
I bring startup-grade engineering quality to every project — clean architecture, robust infrastructure practices, and zero-downtime deployments. From LLM routers to ETL pipelines, I build systems that work reliably at scale with 99.9% uptime.
Currently pursuing a Bachelor of Technology in Computer Science Engineering (2024-28) and available for freelance automation contracts and systems engineering roles. Based in India, working globally.
1+
Years in Automation
1+
Systems Engineered
90%
Cost Reduction
Technical Arsenal
Tools and technologies I use to build production-grade automation pipelines and systems.
Featured Projects
A selection of automation, data engineering, and LLM systems built for speed, cost savings, and scale.
Sieve — Agentic ETL & Data Pipeline
LiveDeveloped an agentic, coded orchestration pipeline with webhooks, form submissions, and webhook triggers. Features multi-channel ingestion, async CRUD, VLM OCR, cryptographic hashing, and vector embeddings. Zero Licensing Overhead (ZLO), FOSS Stack, No SaaS footprint & Negligible-Marginal-Cost Dependency Model.
RAG Conversational Bot
LiveBuilt a custom knowledge-retrieval engine utilizing vector embeddings (RAG) to power an intelligent corporate chatbot with a Telegram Bot API native UI for querying internal database records.
Centralized LLM Router
LiveDeveloped a configuration-driven LLM Router that cuts TTFT latency by up to 90% via semantic KV caching, and reduces input costs by 50-90% through dynamic model tier routing.
Engineering Journey
Freelance Automation & Systems Engineer
2026 – PresentDeveloping configuration-driven LLM Routers that cut TTFT latency by up to 90% via semantic KV caching. Maximizing application uptime to 99.9% and reducing API costs by 50-90% by dynamically routing queries across model tiers.
Agentic ETL & Data Pipeline Engineering
2025 – 2026Built 'Sieve', an agentic ETL data pipeline featuring webhook triggers, programmatic web scraping, asynchronous CRUD, universal conversion, and vision-language model OCR.
RAG & Conversational AI Systems
2025Architected a custom knowledge-retrieval engine utilizing vector embeddings (RAG) to power an corporate chatbot, complete with a responsive Telegram Bot UI for real-time record lookup.
Bachelor of Technology — Computer Science Engineering
2024 – 2028Studying foundational and advanced computer science subjects. Completed Harvard's CS50: Introduction to Computer Science to master computational thinking, memory allocation, and data structures.
Core Expertise
Services I provide to startups, developers, and enterprises looking to automate manual processes and scale their digital architecture.
DevOps & Systems
Infrastructure & DevOps
End-to-end systems architecture utilizing Docker containers, Kubernetes orchestrators (K3s), reverse proxy configuration, and secure CI/CD pipelines.
- Docker & K3s orchestration
- Nginx reverse proxy design
- GitHub Actions CI/CD workflows
- Centralized logging & metrics
Agentic Systems
Automation & RPA Pipelines
High-performance web scrapers, programmatic browser agents, async data workers, and custom web automation routines that eliminate human error.
- Multi-channel scraping agents
- ETL pipeline orchestration
- Vision-language model OCR
- Zero-cost data integration
AI Infrastructure
LLM Systems & AI Integrations
Production-grade LLM routing layers, semantic key-value caching nodes, multi-vector RAG search networks, and custom AI chatbot interfaces.
- Semantic KV caching routers
- LiteLLM API aggregation
- Dynamic fallback protocols
- RAG query optimization
Get In Touch
Let's build something great together
Whether you need an automation pipeline designed, infrastructure orchestrated, or an LLM integration built — I'm here to help. Drop a message and I'll respond promptly.