Available for opportunities

Hello, I'm Parth Panchal AI/ML Engineer

Building production-grade LLM, RAG, and Voice AI systems. Specialized in ML/GenAI pipelines, low-latency inference, and cloud deployment with hands-on ownership from experimentation to production.

View My Work Get In Touch

0 + Years Experience

0 + AI/ML Projects

0 + Certifications

ai_engineer.py

class AIEngineer:
    def __init__(self):
        self.name = "Parth Panchal"
        self.skills = [
            "LLM", "RAG", "Voice AI",
            "PyTorch", "LangChain",
            "Azure", "MLOps"
        ]
        self.analytical_thinker = True
        self.startup_ready = True
    
    def build_ai_systems(self):
        return "Production Ready"

Scroll to explore

Introduction

About Me

3+ Years of
Experience

Engineering the Next Generation of Intelligent Systems

AI/ML Engineer with around 3+ years of experience building production-grade LLM, RAG, and AI/ML systems. Specialized in ML/GenAI pipelines, low-latency inference, and cloud deployment, with hands-on ownership from experimentation to production in startup environments.

I enjoy working in a role that offers diverse challenges, fosters innovation, and allows me to collaborate on cutting-edge AI/ML projects.I thrive in fast-paced environments where I can build and ship AI products that make a real impact.

Voice AI Systems

STT, TTS, Real-time LLM Integration

RAG & LLMs

LangChain, LangGraph, Prompt Engineering

Cloud & MLOps

Azure, AWS, GCP, Docker, MLflow

MLOps & Infra

Docker & Low-latency inference serving.

Career Journey

Work Experience

Machine Learning Engineer

Rootle AI — Voice AI Product Startup

Aug 2025 - Present

Built and optimized real-time voice AI platform integrating STT, TTS, LLMs, and retrieval systems
Designed automated multi-document ingestion and RAG pipeline supporting PDFs, PPTs, and web URLs.
Implemented NVIDIA NV-Ingest for large-scale, heterogeneous knowledge sources
Optimized PyTorch-based inference pipelines, reducing end-to-end latency by ~25%
Fine-tuned and deployed BERT-based intent classifiers for low-latency real-time voice calls

Voice AI LLM RAG PyTorch NV-Ingest BERT

Machine Learning Engineer

Cilans System

May 2023 - Aug 2025

Researched, modified, and deployed ML prototypes across multiple client projects
Designed and deployed end-to-end ML and GenAI pipelines, reducing development turnaround time by ~30-40%
Built LLM-powered document understanding and search workflows using open-source models
Collaborated directly with clients to deliver customized ML and GenAI solutions
Performed exploratory data analysis and feature engineering to improve model performance

Azure AI LangChain TensorFlow fine-tuning GenAI

Data Science Intern

Kron Labs

Nov 2022 - May 2023

Supported data scientists, BI developers, and analysts across data analysis and ML initiatives
Developed computer vision model for deployment on NVIDIA Jetson Nano devices
Collaborated using Git-based workflows for version control and task management

Computer Vision NVIDIA Jetson Python Machine Learning Git

My Work

Featured Projects

Production-grade AI/ML projects showcasing expertise in LLMs, RAG, and cloud deployment

RAG • Azure AI • Production

AI Search Engine(US-based startup)

Next-gen search engine enabling natural-language product discovery. Architected a hybrid RAG system merging text, vector, and image embeddings.

Azure AI Search Hybrid Search Azure ML Cosmos DB

Agentic AI • LangGraph

SocialSyncAgent

Agent-based automation for content curation and social media posting. Multi-source aggregation with human-in-the-loop feedback.

LangChain LangGraph LangSmith Agentic AI Gemini

Document AI • ColBERT

Document Extraction System

End-to-end pipeline for structured data extraction from complex financial PDFs. Led a team of 3-4 engineers managing delivery and client feedback.

Azure ML ColBERT Azure OpenAI PyTesseract OpenCV

Generative AI • LoRA

Jewel.AI

Led development of AI system for image-based jewelry description generation. Fine-tuned Stable Diffusion with LoRA for domain-specific image generation.

Stable Diffusion LoRA Hugging Face Prompt Engineering