Open to opportunities

Tarachand Rahul

@tarachandrahul

Message

I build RAG-powered AI systems that ship fast, scale, and stay low-latency.

Zimbabwe

Message

What I'm looking for

I’m looking to build production RAG/LLM systems with low latency and scalable deployment. I want to own end-to-end pipelines (retrieval, inference, APIs, and reliability), collaborate on measurable performance improvements, and ship features that work in the real world.

I’m an AI Engineer specializing in RAG systems, LLM-integrated backend architectures, and scalable AI applications. I build end-to-end Generative AI pipelines with FastAPI, LangChain, vector databases, and open-source LLMs—always with a production mindset.

My work focuses on semantic retrieval, async backend systems, inference workflows, and scalable AI infrastructure. In projects, I’ve engineered asynchronous FastAPI pipelines (ThreadPoolExecutor), implemented hybrid RAG for multi-turn conversational Q&A, and integrated transcription and embedding workflows to cut manual consumption time by ~60%.

I also enjoy turning AI into reliable products—whether reducing API latency by 50% with caching and async processing or creating offline-capable automation using local LLM planning with resilient fallback execution. I’m driven by latency optimization, robust deployment, and systems that keep performing under real constraints.

Experience

Work history, roles, and key accomplishments

ExcelAgent Automation System

ExcelAgent

Mar 2026 - Apr 2026 (1 month)

Developed an offline AI automation system that converts PDF, images, and raw text into structured Excel spreadsheets using autonomous execution workflows. Implemented local LLM planning with rule-based fallback and a hybrid execution engine with verification, recovery handling, and memory-driven execution.

Python Ollama Prompt Engineering AI Agents Openpyxl Automated Executions Offline Reliability

Speech & Video Intelligence

Speech & Video Intelligence Platform

Jan 2026 - Feb 2026 (1 month)

Built a full-stack AI platform for processing offline video/audio and YouTube content with transcription, embeddings, clustering, summarization, and conversational QA. Engineered an asynchronous FastAPI backend and a hybrid FAISS-based RAG pipeline, reducing manual content consumption time by ~60%.

fastAPI Faiss RAG Whisper LLaMA Flan T5 Asynchronous Embeddings Clustering

Delish Food Delivery Backend

Delish

Jul 2024 - Apr 2025 (9 months)

Architected a scalable food delivery backend using Node.js, MongoDB, and Redis, reducing API latency by 50% through caching and asynchronous processing. Added an AI chatbot for order assistance and menu recommendations and implemented JWT-based authentication with RBAC across 30+ REST APIs.

Node MongoDB Redis Docker JWT RBAC REST APIs CI CD Caching

Education

Degrees, certifications, and relevant coursework

Indian Institute of Information Technology, Sri City

Bachelor of Technology (B.Tech), Computer Science and Engineering

2022 - 2026

Grade: CGPA: 8.71

Activities and societies: Relevant coursework: Machine Learning, Deep Learning, Computer Vision, Natural Language Processing, Data Structures & Algorithms, Linear Algebra, Probability & Statistics, Ethics in AI.

B.Tech in Computer Science and Engineering at IIIT Sri City (11/2022–05/2026) with CGPA 8.71.