About Skills Projects Experience Education Contact
Senior AI Engineer · Ahmedabad, India

Rushabh
Shah

Building production-grade AI systems that go beyond demos — LLMs, RAG pipelines, AI agents, computer vision, and intelligent automation. Research-driven. Execution-focused. Production-obsessed.

17+Production Systems
2yrAI Engineering
10+Industries
95%Workload Reduced
scroll
01 / About

Who I Am

I'm an Applied GenAI & AI Research Engineer with nearly 2 years of hands-on production experience at Brainy Neurals, building systems that operate at scale — not just in notebooks.

My work spans the full modern AI stack: LLMs, RAG pipelines, AI agents, computer vision, voice AI, generative media, and intelligent automation orchestration. From analyzing railway wire parameters at 90 km/h to running fully autonomous 30-stage B2B sales sequences, I build things that work in the real world.

I hold an M.Tech in Artificial Intelligence from IIIT Vadodara and a B.E. in ICT from L.J. Institute of Engineering — backed by teaching assistantship experience and multiple internships across IBM, Arth Infosoft, and others.

"I operate with a research-driven, execution-focused mindset —
bridging business requirements and advanced AI architectures
to deliver measurable impact."
🤖

LLM Systems & RAG

End-to-end pipelines, knowledge graphs, MCP-based workflows, prompt optimization

🧩

AI Agent Orchestration

LangChain, LangGraph, n8n — autonomous multi-agent business process automation

👁️

Computer Vision

Real-time detection, stereo depth measurement, pose estimation, video analytics

🎨

Generative AI

SDXL image gen, Real-ESRGAN upscaling, real-time lip-synced talking avatars

🎙️

Voice & Speech AI

GPT-4o Realtime API, Faster-Whisper ASR, NeMo diarization, ElevenLabs TTS

02 / Skills

Tech Arsenal

A battle-tested stack built across 17 production AI systems spanning 10+ industries.

🤖 AI / ML & Deep Learning
Python PyTorch YOLOv11 OpenCV MediaPipe ZED SDK Faster-Whisper NVIDIA NeMo TensorRT DeepStream FAISS EfficientNet InsightFace FinBERT VADER
🌌 GenAI & LLMs
LangChain LangGraph GPT-4o / 4.1 Google Gemini OpenAI Realtime API Stable Diffusion XL IP-Adapter-FaceID Real-ESRGAN GFPGAN RAG MCP ElevenLabs Fal.ai HeyGen API Vector Search
⚙️ Orchestration & Automation
n8n LangGraph Agents Playwright APScheduler Gmail API Google Sheets API LinkedIn API HubSpot API Slack API Airtable Telegram Bot
🏗️ Backend, Data & Cloud
FastAPI Flask Neo4j MongoDB PostgreSQL BigQuery AWS S3 AWS EC2 Docker CUDA SQLite GStreamer FFmpeg PyMuPDF Streamlit Gradio
03 / Projects

Production AI Systems

17 end-to-end systems built and deployed across industries — each solving a real business problem.

01 EdTech
Australian English AI Tutor
Real-time bi-directional voice AI tutor with specialized Australian accent coaching, automated pronunciation scoring (Grammar / Vocabulary / Pronunciation), and session history analytics.
▸ Eliminated dependency on human tutors · Millisecond feedback loop · Cloud-native & fully scalable
GPT-4o RealtimeSTT/TTSWebSocketsFastAPIMongoDBFlutter
02 Industrial AI
AI Floor Planning Agent
Text-to-floorplan intelligent planning agent. Converts natural language room descriptions into spatially-reasoned coordinate geometry and exports production-ready AutoCAD DXF files.
▸ First draft: hours → seconds · Standardized CAD-ready output · Faster sales approval cycles
Google GeminiLangChainPydanticEzdxf
03 FinTech
Real-Time Stock Signal Predictor
Multi-source sentiment + technical trading engine. Scrapes news & social, transcribes YouTube analysis, calculates RSI/MACD/Volume trends, and produces confidence-scored signals via custom fine-tuned LLM.
▸ Reaction latency: minutes → seconds · Emotion-free confidence-weighted signals · Multi-ticker dashboard
FinBERTVADERFaster-WhisperFastAPIPlotlyPostgreSQL
04 Industrial AI
Railway OHE Measurement System
Real-time vision-based railway overhead wire monitoring. Measures stagger, height & gradient parameters using YOLOv11 + ZED stereo depth at 90 km/h with GPS tagging and tolerance alerts.
▸ 50% targeted pantograph wear reduction · No track possession required · Eliminated manual inspection
YOLOv11ZED Stereo SDKCUDAOpenCVPyQt6
05 Automation
AI Marketing Engine
End-to-end generative ad creative engine for e-commerce. Scrapes product pages → generates AIDA scripts → creates AI images, videos & voiceovers → delivers finished assets to AWS S3 automatically.
▸ 90% manual creative effort eliminated · Weeks → hours production · Massive A/B test scale enabled
GPT-4.1/5Fal.aiElevenLabsn8nAWS S3FastAPI
06 Generative AI
AI Fantasy Avatar Generator
Identity-preserving avatar engine built on SDXL + IP-Adapter-FaceID. Extracts facial embeddings via InsightFace, generates prompt-driven fantasy scenes while preserving face identity, with SSIM-based quality filtering.
▸ Hyper-personalized avatars · Automated QA pipeline · GPU-scalable · Near-zero manual editing
SDXLInsightFaceIP-Adapter-FaceIDFastAPIPyTorch
07 Automation
Automated Meeting Intelligence System
Multi-speaker transcription pipeline with noise removal, speaker diarization, timestamp alignment, and AI-generated structured executive summaries with SRT subtitle export. Integrated with Zoom.
▸ Eliminated manual note-taking · Instant structured meeting minutes · Improved decision tracking
Faster-WhisperNVIDIA NeMoDemucsGeminiPyTorch
08 Computer Vision
Virtual Shoulder Measurement Tool
Camera-based shoulder measurement engine for fashion e-commerce. Uses MediaPipe Pose + Face Mesh for face-calibrated pixel-to-centimeter conversion and automatic size recommendation.
▸ Reduced return rates · Improved checkout confidence · Runs on standard consumer devices
MediaPipe PoseFace MeshOpenCVNumPy
09 Industrial AI
Elevator Parts Similarity Search
Visual similarity search engine for thousands of elevator SKUs. EfficientNet-B0 extracts feature embeddings; FAISS retrieval returns ranked part matches with category prediction in seconds.
▸ Part identification: hours → seconds · Reduced downtime · Democratized expert knowledge
EfficientNet-B0FAISSPyTorchStreamlit
10 B2B Sales
AI Lead Nurturing Automation
30-stage automated AI follow-up engine with reply detection, business-day-aware sequencing, CRM-based personalization, and tone progression across the full sequence — from casual to assertive to final reminder.
▸ 100% follow-up coverage · 10–15 hrs/week saved · Higher reply rates · Zero human intervention
GPT-4.1n8nGmail APIGoogle SheetsHighLevel CRM
11 FinTech
Automated Financial Reporting System
Natural language → SQL → BigQuery execution → finance reports → QuickBooks-ready journal entries. Fully automated monthly close for multi-brand e-commerce, eliminating reconciliation errors.
▸ 95% manual workload reduction · Hours → under 1 minute · Zero reconciliation errors
GPT-4.1BigQueryFastAPIAWS S3n8n
12 Generative AI
Real-Time Talking Avatar
Lip-synced real-time avatar engine combining GPT-4o Realtime speech-to-speech with LIA diffusion-based motion synthesis and HuBERT audio feature extraction for hyper-realistic animated customer interactions.
▸ Hyper-realistic AI engagement · Fully automated animation · Real-time conversational latency
LIA DiffusionGPT-4o RealtimeHuBERTPyTorchCUDA
13 Industrial AI
Civil Beam Counting Automation
PDF beam extraction and annotation engine. Uses regex + spatial proximity logic to detect beams, associate lengths, handle orientation, and produce annotated audit PDFs with a built-in verification layer.
▸ Manual hours → seconds · Eliminated counting errors · Automated audit trail
PyMuPDFPython RegexGradio
14 Automation
LinkedIn Research Automation Pipeline
Fully automated thought leadership pipeline: scrapes arXiv papers → parses PDFs → AI summarizes → schedules and publishes to LinkedIn. Runs 3 posts/week with zero manual drafting effort.
▸ 3 posts/week fully automated · Zero manual drafting · Consistent thought leadership positioning
Gemini 2.0 FlashFastAPIAPSchedulerLinkedIn API
15 Generative AI
AI Image Super-Resolution System
Real-ESRGAN-based 2x/4x upscaling engine for images and video, with GFPGAN face restoration, noise removal, and memory-efficient tiling — turning legacy low-res assets into 4K-ready media.
▸ 4K-ready asset generation · Seconds-level processing · Legacy media monetization
Real-ESRGANGFPGANPyTorchFFmpeg
16 HR Tech
NeuroHire — Graph-Based AI ATS
Knowledge graph-powered applicant tracking system with semantic JD matching, OCR fallback parsing, Neo4j graph modeling, and conversational database querying for natural-language candidate search.
▸ 90% screening time reduction · Semantic candidate ranking · Faster hiring cycles
Gemini 2.0 FlashNeo4jFastAPILangChain
17 Sports AI
AI Basketball Analytics System
End-to-end automated basketball video intelligence pipeline. Multi-model player/ball/net detection, persistent multi-object tracking, team classification, event recognition (shots/assists/steals/blocks), zone-aware scoring, per-player CSV stats, highlight clip generation — targeting 600k+ games/year.
▸ >85% F1 on key events (targeted) · Full analyst workflow automated · Scalable to 600k+ games/yr
DeepStreamTensorRTYOLORF-DETRPyTorchFastAPIAWS S3LangChainGemini
04 / Experience

Work History

Apr 2026 – Present Brainy Neurals Pvt. Ltd.
Senior AI Engineer
📍 Ahmedabad, Gujarat
  • Leading production AI system design and deployment across multiple client verticals
  • Architecting multi-agent orchestration systems, agentic automation pipelines, and LLM-powered workflows
  • Mentoring junior engineers and setting technical direction for AI development
Jun 2024 – Apr 2026 Brainy Neurals Pvt. Ltd.
AI Research Engineer
📍 Ahmedabad, Gujarat
  • Delivered 17+ production AI PoCs and full systems across computer vision, LLMs, RAG, generative AI, and automation
  • Led Railway OHE Measurement project with YOLOv11, ZED SDK stereo vision and OpenCV — measuring wire parameters at 90 km/h
  • Built identity-preserving avatar generator using SDXL + IP-Adapter-FaceID, turning user photos into fantasy avatars
  • Designed RAG systems for document queries using Google Gemini across recruitment, tutoring, and marketing verticals
  • Developed AI meeting minutes generator with multi-speaker diarization (Faster-Whisper + NeMo) integrated with Zoom
  • Built real-time talking avatar using OpenAI Realtime API, LIA diffusion, and HuBERT for lip-sync from static images
  • Created OCR-based medical report parser using PyMuPDF, regex, and LLMs; shoulder measurement tool via MediaPipe
Sep 2023 – May 2024 IIIT Vadodara
Teaching Assistant
📍 Gandhinagar, Gujarat
  • Assisted faculty in teaching and assessment for AI/ML coursework at postgraduate level
Sep 2023 – Oct 2023 Sarva Suvidhaen Pvt. Ltd.
Django Developer
📍 Remote · Patna, Bihar
  • Built REST APIs and backend features for CMS and Gyan projects; created frontend pages using HTML/CSS
Jun 2023 – Jul 2023 IBM (via AICTE / Edunet Foundation)
AI Intern
📍 Virtual · Greater Delhi Area
  • Completed practical AI/ML training; built a Mental Fitness Tracker that identifies cause/pattern of mental illness from patient data
Jan 2023 – May 2023 Arth Infosoft Pvt. Ltd.
Python Developer
📍 Ahmedabad, Gujarat
  • Built a Time Tracking Web Application — project managers schedule tasks, developers submit via portal
Jun 2022 – Jul 2022 Grownited Pvt. Ltd.
Django Developer
📍 Ahmedabad, Gujarat
  • Developed an e-commerce shopping website with user auth, product catalog, and session management
05 / Education

Academic Background

M.Tech · 2023 – 2025
Master of Technology
Artificial Intelligence
Indian Institute of Information Technology Vadodara
Sep 2023 – Sep 2025 · Gandhinagar, Gujarat
B.E. · 2019 – 2023
Bachelor of Engineering
Information & Communication Technology
L.J. Institute of Engineering and Technology
Aug 2019 – Jun 2023 · Ahmedabad, Gujarat
06 / Certifications

Credentials

🏆
Microsoft Learn AI Skills Challenge
Microsoft
Certificate of Achievement
IBM / AICTE / Edunet Foundation
Prompt Compression and Query Optimization
Professional Certification
Introduction to Relational Databases and SQL
Professional Certification
Introduction to Blockchain Technologies
Professional Certification
Let's Build
Something Real.

Open to collaborating on GenAI products, agentic automation, deep learning deployments, and consulting on production AI systems.

Or reach out directly at rushabhshah122000@gmail.com