🚀 I'm a CS sophomore at VIT Amaravati specializing in AI & ML, with hands-on experience designing distributed systems, autonomous multi-agent pipelines, and high-performance AI-integrated applications. Comfortable with Docker containerization, Kubernetes orchestration, and horizontal scaling for reliable, production-grade infrastructure. From LangGraph-orchestrated prediction pipelines and self-healing AGI systems to ESP32-powered smart glasses and a full video editing & content strategy practice (Editor Cyclops) — I build end-to-end, from silicon to software to screen.
|
🏅 VIT Internal Expo Smart Vision Aid Selected |
🎓 CGPA 8.22 B.Tech CS · AI & ML |
🤖 9 AI Projects Shipped & Deployed |
📈 LangGraph 8-Node Distributed Pipelines |
🎬 50+ Edits Editor Cyclops · 3+ Yrs |
class AnkitSengupta:
def __init__(self):
self.name = "Ankit Sengupta"
self.role = "AI Engineer & Backend Developer"
self.university = "VIT Amaravati · Class of 2028"
self.cgpa = 8.22
self.skills = {
"AI / ML" : ["RAG Pipelines", "AI Agents", "LangGraph", "LangChain",
"TensorFlow", "YOLO", "OpenCV", "XGBoost", "RL Feedback"],
"LLM Infra" : ["LangSmith", "ChromaDB", "FAISS", "Qdrant", "HuggingFace",
"Gemma-4", "MedGemma-4B", "Phi-3", "Prompt Engineering", "Vector Embeddings"],
"Systems" : ["Distributed Systems", "Concurrency & Multi-threading", "Docker",
"Kubernetes", "Self-Healing Architecture", "Fault Tolerance"],
"Backend" : ["Django", "FastAPI", "Flask", "Node.js",
"MongoDB", "WebSockets", "APScheduler", "Neo4j", "Redis"],
"Languages" : ["Python", "C", "C++", "JavaScript", "TypeScript", "Java", "Dart", "MATLAB"],
"Mobile" : ["Flutter", "Android", "Kotlin", "Firebase"],
"Embedded" : ["ESP32", "Arduino", "C++", "IoT Sensors"],
"Video Editing": ["Premiere Pro", "After Effects", "DaVinci Resolve", "Motion Design"],
}
self.trophy = "🏅 Selected · VIT Internal Expo 2025"
self.superpower = "ML theory → production systems, and story → screen"
self.status = "🟢 Open to internships & collaborations!"
def say_hi(self):
print("Let's build something that matters 🚀")Self-Employed · Remote · 2023 — Present
Independently run an end-to-end video editing and content strategy practice under the brand Editor Cyclops, serving 10+ creator-economy clients with short-form content for Instagram Reels, YouTube Shorts, and brand campaigns.
| 🎯 Production Pipeline | Manage end-to-end editing pipelines for 10+ concurrent clients — from brief and rough cut to final delivery across vertical, horizontal, and square formats |
| ⚡ Signature Style | Fluent in Devin Jatho-style editing — rhythm-locked cuts, deliberate colour contrast, beat-synced motion, and raw, hook-first energy |
| 🍎 Motion & UI Design | Apple-style Glass UI / liquid-glass animations, kinetic typography, and layered motion graphics for app promos and brand clips |
| 📊 Data-Driven Strategy | Apply engagement data to editing decisions — pacing, hooks, and colour treatment tuned to platform-native performance |
| 🚀 Client Ownership | Full project ownership and client-facing leadership; ships deliverables on tight deadlines across multiple concurrent workflows |
| 📈 Track Record | 50+ projects delivered · 100% client satisfaction / repeat clients · tools mastered: Premiere Pro, After Effects, DaVinci Resolve |
Process: Discovery Call → Creative Strategy (hook structure, pacing, colour) → Production (edit, motion graphics, sound design, VFX) → Delivery (revisions + platform-ready exports)
🎬 View Portfolio → · 📸 @editorcyclops on Instagram →
── 🤖 AI & Intelligence ──
── 🔗 LLM Orchestration & RAG ──
── 🐳 Systems & Infrastructure ──
── 🌐 Backend & Web ──
── 💻 Languages & Frameworks ──
── 📱 Mobile & Embedded ──
── 🎬 Video Editing & Motion Design (Editor Cyclops) ──
🔥 "Every project is a chance to bridge theory and real-world impact"
A high-performance, modular, locally-hosted Autonomous General Intelligence OS — self-healing, horizontally scalable, and containerized — that reasons, remembers, monitors the world, teaches, and assists with clinical questions, without sending a single byte to the cloud.
| 🧠 General Chat | Local Llama/Qwen models for general-purpose reasoning — fully offline |
| 🏥 Health Track | MedGemma 4B isolated pipeline with SigLIP vision for X-ray & clinical reasoning; FHIR-compatible EHR; zero patient data exfiltration |
| 🎓 Education Track | Adaptive Tutor with OCR-powered homework grading, dynamic quiz generation, and culturally localized content for India/SE Asia |
| 🌍 World Monitor | Live GDELT + USGS feeds → AI-synthesized geopolitical & disaster briefings + country instability scoring |
| 🕸️ Mirofish Graph | Force-directed semantic knowledge graph with Leiden community detection — visualize your entire knowledge base |
| 🎙️ Jarvis Voice | Local Whisper STT + Kokoro/ONNX TTS — full duplex with interrupt support |
| 📂 ACE Knowledge Vault | Obsidian-compatible vault (Atlas / Calendar / Efforts) — every AI interaction compounds into personal memory |
| 🛠️ Self-Healing Ops | Automatic health monitoring, failure detection, and service restart logic maintaining uptime across all distributed pipeline components |
| 🐳 Containerized Deploy | Fully Dockerized services with Kubernetes concepts applied for service orchestration and horizontal scaling |
| 🚀 Edge Deployment | Runs on Windows 10/11, Android, Raspberry Pi 5, and NVIDIA Jetson — no cloud required |
| ⚡ Performance | 60+ tokens/sec (RTX 3070+) · MedGemma 4B ~6GB VRAM · Cold start < 8s · 10,000+ graph nodes tested |
+─────────────────────────────────────────────────────────────────────────+
│ CYBORG AGI ARCHITECTURE │
+─────────────────────────────────────────────────────────────────────────+
│ │
│ Frontend Shell (Flutter 3.x) │
│ Dashboard · World Monitor · Mirofish Graph · Jarvis Voice · Settings │
│ ↕ REST / WebSocket │
│ Backend Intelligence (FastAPI + Python, Dockerized, self-healing) │
│ General Chat │ MedGemma 4B │ Adaptive Tutor │ KGE │ World Monitor │
│ ↕ │
│ Knowledge Vault (ACE / Obsidian Structure) │
│ .md Semantic Nodes · Wikilink Graph · FHIR EHR Store │
│ │
│ TRACKS: │
│ 🏥 Health → MedGemma 4B (SigLIP Vision) → FHIR EHR (isolated) │
│ 🎓 Education → Gemma 4 Tutor → OCR Grader → Quiz Generator │
│ 🌍 Resilience → GDELT + USGS → World Monitor → Instability Index │
│ │
│ DEPLOY: Docker · Kubernetes concepts · Windows · Android · Pi · Jetson│
+─────────────────────────────────────────────────────────────────────────+
🏆 Built for the Gemma 4 Good Hackathon · Kaggle × Google DeepMind · Targeting Health, Education & Global Resilience tracks · V1.0 Stable · View Repo →
AI-powered stock direction prediction using an 8-node distributed agent pipeline — real-time news, LLM reasoning, RAG pipelines, concurrency & multi-threading, and reinforcement learning feedback
| 🔗 Orchestration | 8-node distributed LangGraph pipeline: fetch → sentiment → embed → stock → RAG → LLM → ML → ensemble, using concurrency & multi-threading to parallelize data ingestion and analysis across asynchronous nodes |
| 🧠 LLM Core | Gemma-3-4B-IT (local HuggingFace) for news reasoning & directional prediction |
| 📦 RAG Layer | ChromaDB / FAISS vector store + sentence-transformers all-MiniLM-L6-v2 embeddings |
| 🤖 ML Model | Reward-weighted XGBoost binary direction classifier — combines with LLM for ensemble final call |
| 🔁 RL Feedback | Custom reward loop: record → resolve → retrain XGBoost on real outcomes after 3 days, improving prediction reliability at scale |
| 🌐 Backend | FastAPI + WebSockets (real-time pipeline streaming) + APScheduler background jobs |
| 📊 Frontend | React + Vite + TailwindCSS trading UI — candlestick charts, live price feed, sentiment gauge |
| 🔍 Observability | LangSmith tracing for full LangGraph pipeline visibility |
+------------------------------------------------------------------+
| NEWS SOURCES: NewsAPI · GNews · AlphaVantage |
+----------------------------+-------------------------------------+
|
v
| LANGGRAPH: fetch_news → analyse_sentiment → embed_store |
| → fetch_stock → rag_retrieve → llm_reason |
| → ml_predict → final_predict |
| [ Gemma-3-4B LLM ] + [ ChromaDB RAG ] + [ XGBoost ] |
|
+--------------+--------------+
v v
FastAPI + WebSocket React Trading UI
|
v
RL FEEDBACK LOOP → Record → Resolve → Reward → Retrain
An AI Teams co-pilot that turns meeting transcripts into structured, searchable knowledge — surfacing decisions and action items instead of buried recordings
| 🎙️ Meeting Ingestion | Captures & processes Teams meeting transcripts in real time into a structured knowledge base |
| 🔍 Natural-Language Search | RAG-style retrieval lets users query past meetings conversationally instead of rewatching recordings |
| ✅ Action-Item Extraction | Automatically surfaces decisions and follow-up tasks from meeting content |
| 🏆 Origin | Built for a Microsoft Hackathon |
A security OS for fleets of AI agents — modelling agent-to-agent behaviour as a graph to detect and respond to anomalies in real time
| 🕸️ Agent Graph Modelling | Neo4j graph database models agent-to-agent communication and trust relationships across the swarm |
| ⚡ Real-Time Event Pipeline | Redis-backed low-latency state and event streaming for live monitoring of agent behaviour |
| 🔗 LangGraph Orchestration | Coordinates detection and response workflows across the agent mesh |
| 🖥️ Security Dashboard | React frontend surfaces anomalies, agent activity, and mesh health in real time |
| 🏆 Origin | Built for a security-focused hackathon |
Real-time AI-powered assistive smart glasses with synchronized multi-threaded ultrasonic telemetry — giving spatial freedom to the visually impaired
| 📷 Vision System | 3× synchronized ESP32-CAM modules + ultrasonic sensors → full 360° spatial coverage with multi-threaded telemetry |
| ⚡ AI Detection | YOLO real-time object detection for sub-100ms obstacle identification |
| 📱 Mobile App | Android companion (Java/Kotlin) with live audio alerts & navigation feedback |
| 🔧 Embedded Core | C++ on Arduino IDE for ultra-low-latency, concurrency-safe performance |
| 🏅 Achievement | Selected for VIT Amaravati Internal Expo |
AI-powered platform connecting farmers and buyers through intelligent crop analysis
| 🔬 ML Pipeline | TensorFlow model trained on crop dataset; Pandas for feature engineering and yield trend analysis |
| 👁️ Computer Vision | OpenCV disease detection pipeline with confidence scoring |
| 🌐 Backend Marketplace | Django/Flask REST API connecting farmers with buyers; order management, inventory tracking, and ML-driven pricing logic |
Zero-effort expense tracking by securely parsing your bank transaction SMS
| 💬 Core | Securely parses bank SMS for automatic expense categorization |
| 📈 Dashboard | Real-time financial insights with visual breakdowns |
| 🔐 Security | Firebase auth + encrypted cloud backup |
Emotion intelligence meets medical data — sentiment analysis + real-time report parsing
| 💬 NLP Engine | TensorFlow sentiment analysis for real-time emotional state detection |
| 📄 OCR Pipeline | Pytesseract extracts & structures data from medical reports |
| 🔗 Intelligence | Cross-references health info with curated medical datasets |
Your AI-powered symptom tracker, medication guide, and health companion
| 🔍 Symptom Match | Fuzzy logic symptom matching via FuzzyWuzzy |
| 💊 Health Tracking | Symptoms, medications & personalised diet recommendations |
| 🖥️ Interface | Clean Tkinter GUI with CSV dataset integration |
| 🏅 | 🎓 | 🤖 | 🔗 | 🐳 | 🎬 |
|---|---|---|---|---|---|
| VIT Internal Expo | CGPA 8.22 | AI & ML | LLM Infra | Distributed Systems | Editor Cyclops |
| Smart Vision Aid Selected | B.Tech CS · 2028 | RAG · Agents · YOLO | LangGraph · Qdrant · RL | Docker · Kubernetes | 50+ Edits · 3+ Yrs |
╔══════════════════════════════════════════════════════════════════════╗
║ 🧭 On My Workbench ║
╠══════════════════════════════════════════════════════════════════════╣
║ 🧠 Cyborg AGI — Local AGI OS · Gemma 4 Hackathon · V1.0 Stable ║
║ MedGemma 4B · Adaptive Tutor · World Monitor · Mirofish Graph ║
║ Self-healing · Dockerized · Kubernetes-orchestrated ║
║ 📈 NewsAlphaAI — LangGraph Distributed Stock Prediction ✅ Shipped ║
║ 🧭 MeetMind — AI Teams Co-Pilot ✅ Shipped (Microsoft Hackathon) ║
║ 🛡️ mesh_guard — AgentOps Security Mesh ✅ Shipped (Security Hack) ║
║ 🎬 Editor Cyclops — Video Editing & Content Strategy ✅ Ongoing ║
║ 🤖 Autonomous AI Agent Systems with Tool Use ║
║ 📚 Retrieval-Augmented Generation (RAG) Pipelines ║
║ ⚡ Scalable Distributed Backends · FastAPI / Django / Node ║
║ 🔗 LLM Orchestration · LangGraph / LangChain ║
║ 🐳 Containerization & Orchestration · Docker / Kubernetes ║
╚══════════════════════════════════════════════════════════════════════╝
