Skip to content

Arun Karthik BT

AI Engineer · 10xScale.ai

Hyderabad, Telangana, India

[01] Professional Summary

AI Engineer with hands-on experience building and shipping production LLM systems — multi-agent orchestration, RAG and hybrid retrieval, and real-time voice agents. Designs agentic backends with LangGraph, AgentFlow and MCP/FastMCP, drives structured extraction over large document corpora with Gemini and Vertex AI, and cost-optimises inference by replacing LLM calls with deterministic parsers where accuracy allows.

[02] Experience

AI Software Engineer

Jul 2026 — Present

10xScale.ai · Hyderabad

Nirnaya, a legal investigation platform: FastAPI and TaskIQ/Redis pipelines that parse 1,000+ court and registry PDFs into PostgreSQL, deterministic parsers in place of per-document LLM calls, identity resolution with hard vetoes before fuzzy scoring, and a Chrome extension for data collection. Also an AI tutoring platform: low-latency LiveKit voice, adaptive multi-agent routing on AgentFlow, and MCP tools via FastMCP.

AI Intern

Jul 2025 — Dec 2025

10xScale.ai · Hyderabad

Built a dual-mode medical chatbot with multimodal report analysis (Gemini 2.5 Flash, AgentFlow), a database agent with MCP tools on LangGraph, and a pgvector RAG chatbot over 200+ PDFs.

AI Intern

Apr 2024 — Jun 2024

FourKites · Chennai

Built a multi-agent CrewAI workflow converting XML, CSV and Excel inputs into structured JSON, and used Virtuoso for AI-powered application testing.

[03] Education

B.E. (Hons.) Electrical and Electronics Engineering

BITS Pilani, Hyderabad Campus · Hyderabad

Class XII: Sri Vignesh Vidyalaya (84.6%). Class X: Alpha Wisdom Vidyashram (91.8%).

[04] Technical Skills

GenAI & Agentic AI

LangGraph · LangChain · CrewAI · AgentFlow · MCP / FastMCP · LlamaIndex · Multi-Agent Orchestration · RAG & Hybrid RAG · Prompt Engineering · Structured Output · Tool Calling · Cost Optimisation

Models & Voice

Gemini 2.5 / Vertex AI · Groq (Llama 3) · OpenAI-compatible APIs · Google Cloud STT & TTS · LiveKit · VAD

Retrieval & Data

Qdrant · pgvector · ChromaDB · Embeddings · Semantic Search · Knowledge Graphs · PyMuPDF · spaCy NER · Entity Resolution

Backend & Infrastructure

FastAPI · PostgreSQL · Tortoise ORM · Redis · TaskIQ / Celery · Apache Airflow · BigQuery · DBT · WebRTC / WebSockets

Languages

Python · SQL · TypeScript · JavaScript · C · Java (familiar)

Cloud & Dev Tools

GCP · AWS · Docker · Git · GitHub Actions · Pytest · Pandas · NumPy · Streamlit

[05] Selected Projects

Nirnaya — Legal Intelligence

Court and registry records are scattered across portals as unstructured PDFs and HTML. 1,000+ documents from eCourts, Supreme Court, NCLT, DRT, CERSAI and MCA normalised into PostgreSQL, with deterministic parsers cutting LLM cost and latency.

Stack: FastAPI, TaskIQ, Gemini, PostgreSQL, WXT

AI Tutoring Platform

Students needed real-time voice tutoring that adapts to what they are doing. Low-latency WebRTC audio with VAD-based cost control and agents that switch between video Q&A, live coding and study planning.

Stack: LiveKit, Vertex AI, AgentFlow, FastMCP, Qdrant

Database AI Agent

Non-technical users can't query diverse database schemas. Natural-language querying across schemas with a query-understanding preprocessing layer.

Stack: LangGraph, MCP, SQL

RAG Chatbot & Medical Assistant

Answers needed to be grounded in 200+ PDFs and in patient reports and imaging. Semantic retrieval-augmented answering, plus patient/expert modes with database-backed appointment scheduling.

Stack: pgvector, Gemini 2.5 Flash, AgentFlow