AI Localization Consultant @ Pratilipi Comics
Aspiring: AI Engineer (MLOps, AIOps, LLMOps & Agents) | Recent CS Graduate @DSU Bangalore | 6+ AI Systems Built | 1 Patent + 1 Publication
| Project | Type | Key Tech | Links |
|---|---|---|---|
| VedicMed AI Assistant |  |
Groq Vision, ElevenLabs, Gradio | 📂 Repo |
| Compliance-GPT |  |
Weaviate, FastAPI, Groq | 📂 Repo • 🧪 Tests • 🐳 Docker • 🚀 Demo |
| AudioRaG Enterprise |  |
AssemblyAI, Qdrant, SambaNova | 📂 Repo |
| TruthTracker (AntiAi) |  |
EfficientNet-B4, FastAPI, React | 📂 Repo |
| AI Real Estate Agent |  |
Gemini AI, Firecrawl, Redis | 📂 Repo |
╔══════════════════════════════════════════════════════════════════════════════╗
║ 🎯 SOLVING REAL AI PROBLEMS 🎯 ║
╚══════════════════════════════════════════════════════════════════════════════╝
| Your Need | My Solution | Where I've Proven It |
|---|---|---|
 |
Citation-backed, hallucination-reduced RAG pipelines | Compliance-GPT, AudioRaG Enterprise |
 |
Prompt engineering, multi-model orchestration | GPT-4o, Claude, Llama, Gemini projects |
 |
FastAPI + Docker + Cloud deployments | 6+ systems built with production standards (Docker, CI/CD, monitoring) |
 |
Vision + Audio + Text fusion systems | Medical Chatbot, Audio-RAG |
 |
Hindi/Telugu/Kannada NLP for Indic language market | Pratilipi Comics localization |
 |
Academic rigor meets industry speed | 1 Patent + 1 Publication |
╭─────────────────────────────────────────────────────────────────╮
│ "Stable, deployment-ready AI systems with Docker, CI/CD, │
│ automated testing, and monitoring for real-world impact" │
╰─────────────────────────────────────────────────────────────────╯
I structure AI/ML projects through a rigorous, business-driven methodology that ensures reliability, scalability, and real-world impact. My systems are designed to be stable and deployment-ready, incorporating containerization (Docker), automated testing, CI/CD pipelines, and monitoring capabilities:
1. Business Requirements & Problem Validation
┌─────────────────────────────────────────────────────────────┐
│ STEP 1: VALIDATION │
├─────────────────────────────────────────────────────────────┤
│ • Define core business problem and quantifiable ROI │
│ • Research existing solutions and competitive advantages │
│ • Establish success criteria (latency, accuracy, cost) │
└─────────────────────────────────────────────────────────────┘
- Define the core business problem and quantifiable ROI metrics
- Research existing solutions and identify competitive advantages
- Establish success criteria (latency SLAs, accuracy thresholds, cost per prediction)
2. Reliability & Quality Strategy
┌─────────────────────────────────────────────────────────────┐
│ STEP 2: QUALITY │
├─────────────────────────────────────────────────────────────┤
│ • Hallucination reduction mechanisms │
│ • Error handling and fallback systems │
│ • Evaluation metrics aligned with business KPIs │
└─────────────────────────────────────────────────────────────┘
- Implement hallucination reduction mechanisms (RAG, fine-tuning, prompt engineering, validation layers)
- Design robustness strategies (error handling, fallback mechanisms, circuit breakers)
- Define evaluation metrics aligned with business KPIs
3. System Design & Architecture
┌─────────────────────────────────────────────────────────────┐
│ STEP 3: ARCHITECTURE │
├─────────────────────────────────────────────────────────────┤
│ • Optimize latency, throughput, scalability │
│ • Model selection vs API trade-offs │
│ • Infrastructure and cost optimization │
└─────────────────────────────────────────────────────────────┘
- Optimize for latency, throughput, and scalability requirements
- Evaluate model selection vs. API trade-offs (local deployment vs. cloud APIs)
- Design infrastructure (compute resources, caching, database schema)
- Plan cost optimization and resource utilization
4. Evaluation & Benchmarking
┌─────────────────────────────────────────────────────────────┐
│ STEP 4: BENCHMARKING │
├─────────────────────────────────────────────────────────────┤
│ • Baseline metrics and comparative analysis │
│ • A/B testing and validation │
│ • Production-representative data testing │
└─────────────────────────────────────────────────────────────┘
- Establish baseline metrics (accuracy, precision, recall, F1-score, latency)
- Perform comparative analysis against baselines and competitors
- Conduct A/B testing and validation on hold-out datasets
- Use production-representative data for realistic assessment
5. Integration & Deployment
┌─────────────────────────────────────────────────────────────┐
│ STEP 5: DEPLOYMENT │
├─────────────────────────────────────────────────────────────┤
│ • Clean APIs with documentation │
│ • CI/CD pipelines for automated testing │
│ • Blue-green / Canary rollout strategies │
└─────────────────────────────────────────────────────────────┘
- Design clean APIs with comprehensive documentation
- Ensure backward compatibility and semantic versioning
- Implement CI/CD pipelines for automated testing and deployment
- Plan rollout strategy (blue-green or canary deployments)
6. Production Monitoring & Observability
┌─────────────────────────────────────────────────────────────┐
│ STEP 6: MONITORING │
├─────────────────────────────────────────────────────────────┤
│ • Real-time metrics and distributed tracing │
│ • Alerting for SLA violations │
│ • Rate limiting and graceful degradation │
└─────────────────────────────────────────────────────────────┘
- Monitor real-time metrics (latency, error rates, token usage, cost)
- Implement comprehensive logging and distributed tracing
- Set up alerting for SLA violations and anomalies
- Handle concurrent users with rate limiting and graceful degradation
7. Continuous Improvement
┌─────────────────────────────────────────────────────────────┐
│ STEP 7: ITERATION │
├─────────────────────────────────────────────────────────────┤
│ • Production data analysis and feedback loops │
│ • Performance and cost optimization │
│ • Model retraining and feature development │
└─────────────────────────────────────────────────────────────┘
- Analyze production data and user feedback
- Iterate on model performance with real-world insights
- Optimize costs and performance based on deployment data
- Maintain feedback loops for model retraining and feature development
| Principle | Why It Matters | How I Apply It |
|---|---|---|
 |
Anyone can run notebooks. Few can build stable, deployment-ready systems. | Every project I build has deployment-ready architecture (Docker, FastAPI, testing) from day one. |
 |
70-85% of AI initiatives fail to meet expected outcomes due to trust issues. | My RAG systems use citation-backed answers — every claim is traceable to a source. |
 |
600M+ potential Indic language market, <0.1% AI coverage. | Building localization pipelines at Pratilipi for underserved language users. |
 |
Users don't wait. If it's slow, it's broken. | Hybrid search (BM25 + semantic), caching, and optimized inference pipelines to ensure sub-second response times. |
 |
Can't improve what you can't measure. | RAGAS evaluation, latency monitoring, accuracy benchmarks in every project. |
╔═══════════════════════════════════════════════════════════════════════════════╗
║ ║
║ GOAL: Evolve into a full-fledged AI/ML Architect specializing in ║
║ AI Ops, MLOps, and LLMOps — building the stable, scalable ║
║ backends that power the next generation of AI systems. ║
║ ║
╚═══════════════════════════════════════════════════════════════════════════════╝
I am not just building models; I am building the infrastructure that makes them reliable. My roadmap focuses on:
- AI Ops & Observability: Mastering the art of monitoring, logging, and debugging complex AI pipelines in production.
- LLM Ops: Building robust evaluation frameworks and deployment pipelines for Large Language Models.
- Scalable Backends: Architecting distributed systems that can handle millions of inferences with high availability.
╭──────────────────────────────────────────────────────────────────────────────╮
│ │
│ ████ ████ ████ ██ ████ ████ ██████ ████ │
│ █ █ █ █ █ █ █ █ █ ██ █ │
│ ████ ████ █ █ █ ███ █ ██ ████ │
│ █ █ █ █ █ █ █ █ █ ██ █ │
│ █ █ █ ████ ██ ████ ████ ██ ████ │
│ │
╰──────────────────────────────────────────────────────────────────────────────╯
┌─────────────────────────────────────────────────────────────────────────────┐
│ PROBLEM │ Need for accessible AI-powered medical consultation demos │
│ │ that combine voice, vision, and text modalities │
├────────────┼────────────────────────────────────────────────────────────────┤
│ SOLUTION │ Multimodal chatbot: speak symptoms, upload images, │
│ │ receive AI diagnosis in text + realistic voice response │
└────────────┴────────────────────────────────────────────────────────────────┘
- Tech: Groq Whisper (ASR) | Groq LLaMA Vision | ElevenLabs TTS | Gradio
- Features: Voice-to-text symptom input, medical image analysis (skin conditions), realistic voice responses
- Architecture:
voice_of_the_patient.py→brain_of_the_doctor.py→voice_of_the_doctor.py - Educational: Demonstrates multimodal AI integration for healthcare use cases
┌─────────────────────────────────────────────────────────────────────────────┐
│ PROBLEM │ Compliance teams spend significant time manually searching │
│ │ regulations, costing companies substantial resources │
├────────────┼────────────────────────────────────────────────────────────────┤
│ SOLUTION │ AI-powered assistant with citation-backed answers in 2 seconds │
│ │ significantly reducing research time │
└────────────┴────────────────────────────────────────────────────────────────┘
- Tech: FastAPI | Weaviate (BM25 + semantic) | Groq LLM | Docker
- Features: Smart query expansion, web search fallback, response caching, admin auth, rate limiting
- Security (v2.1): HTTPS enforcement, CORS protection, audit logging, Prometheus metrics
- Live Demo
┌─────────────────────────────────────────────────────────────────────────────┐
│ PROBLEM │ Organizations can't efficiently query insights from │
│ │ audio/meeting recordings at scale │
├────────────┼────────────────────────────────────────────────────────────────┤
│ SOLUTION │ Enterprise audio RAG with transcription, semantic search, │
│ │ and conversational AI over audio content │
└────────────┴────────────────────────────────────────────────────────────────┘
- Tech: AssemblyAI (speaker diarization) | Qdrant Vectors | SambaNova LLM | Redis Cache
- Enterprise Features: JWT auth with RBAC, multi-tenant isolation, audit logs, batch processing
- Domain Models: Healthcare, Legal, Finance vocabularies with privacy-conscious design
- Architecture: Streamlit UI + FastAPI + PostgreSQL + Celery workers
┌─────────────────────────────────────────────────────────────────────────────┐
│ PROBLEM │ Disinformation spreads faster than fact-checkers can respond │
├────────────┼────────────────────────────────────────────────────────────────┤
│ SOLUTION │ AI platform combining NLP + Computer Vision to detect │
│ │ fake news articles and deepfake images with explainability │
└────────────┴────────────────────────────────────────────────────────────────┘
- Tech: EfficientNet-B4 | MTCNN Face Detection | Ensemble ML (LR + RF + GB) | React + TypeScript
- Features: LIME explainability, GradCAM heatmaps, real-time confidence scores
- Inspired by: IFCN fact-checking principles
- API: FastAPI with Swagger docs at
/docsand/redoc
┌─────────────────────────────────────────────────────────────────────────────┐
│ PROBLEM │ Property research is manual, time-consuming, and expensive │
├────────────┼────────────────────────────────────────────────────────────────┤
│ SOLUTION │ Multi-agent AI system for automated property discovery, │
│ │ investment analysis, and market trend predictions │
└────────────┴────────────────────────────────────────────────────────────────┘
- Tech: Gemini AI | Firecrawl API | Streamlit | SQLite/PostgreSQL | Redis
- Features: ROI projections, rental yields, risk scoring, market trends, search history
- Data Sources: Real-time scraping from 99acres, Housing.com, Square Yards
- Performance: Significant API cost reduction with intelligent Redis caching
╔══════════════════════════════════════════════════════════════════════════════╗
║ ║
║ ⚡ TECH ARSENAL ⚡ ║
║ ║
╚══════════════════════════════════════════════════════════════════════════════╝
╭──────────────────────────────────────────────────────────────────────────────╮
│ │
│ 🌍 LANGUAGES: English | Hindi | Telugu | Kannada | Japanese (Intermediate) │
│ │
╰──────────────────────────────────────────────────────────────────────────────╯
Audio & Speech AI
| Project | Description | Stack |
|---|---|---|
| Audio-RAG-Analyzer | Audio content analysis with RAG | Python, Transformers |
| Audio-AI-Agent | Intelligent audio processing agent | AI Agents |
NLP & Creative AI
| Project | Description | Stack |
|---|---|---|
| Narrative Transformer | AI-powered story genre transformation with custom NTI metric | Transformers, LLMs |
Healthcare AI
| Project | Description | Stack |
|---|---|---|
| Healthcare_ChatBot | Domain-specific healthcare assistant | Python, NLP |
| HealthyfyMe | Health and wellness application | Python, ML |
Document Intelligence
| Project | Description | Stack |
|---|---|---|
| LLMBasedPDF | LLM-powered PDF processing | LLMs |
| TextSummarizer_Project | Intelligent text summarization | NLP, Transformers |
| DocumentRetrieval | Smart document retrieval system | Information Retrieval |
Full-Stack Apps
| Project | Description | Stack |
|---|---|---|
| Edu-Connect-Dev | Educational platform | React |
| gdp-dashboard | Data visualization dashboard | Streamlit |
╔══════════════════════════════════════════════════════════════════════════════╗
║ ║
║ 🚀 CAREER JOURNEY 🚀 ║
║ ║
╚══════════════════════════════════════════════════════════════════════════════╝
|
|
|
|
╔══════════════════════════════════════════════════════════════════════════════╗
║ ║
║ 🔬 RESEARCH CONTRIBUTIONS 🔬 ║
║ ║
╚══════════════════════════════════════════════════════════════════════════════╝
A System for Providing Security Using a Plurality of Factors for IoT Gadgets
Filed (Indian Patent No. 202341040746)
Discovering Insights into Heart Health: A Survey of Data Mining and Machine Learning Methods
Presented at ICCICCT-2023 NICHE
╭──────────────────────────────────────────────────────────────────────────────╮
│ │
│ B.Tech in Computer Science & Technology │
│ Dayananda Sagar University | First Class │
│ 2021–2025 │
│ │
╰──────────────────────────────────────────────────────────────────────────────╯
╔══════════════════════════════════════════════════════════════════════════════╗
║ ║
║ 📚 LEARNING & GROWING 📚 ║
║ ║
╚══════════════════════════════════════════════════════════════════════════════╝
-8E75B2?style=for-the-badge){kind=icon}
-FFD21E?style=for-the-badge){kind=icon}
╭───────────────────────────────────────────────────────────────────────────────────────╮
│ │
│ OPEN TO: AI/ML Intern | Entry-Level AI Engineer | LLMOps Entry Level │
│ Entry Level RAG Systems Developer | Founder Office - AI Engineer │
│ Product Development Associate or Intern │
│ │
│ LOCATION: Bengaluru, India (Open to Remote) │
│ │
╰───────────────────────────────────────────────────────────────────────────────────────╯
╔══════════════════════════════════════════════════════════════════════════════╗
║ ║
║ ║
║ “🎆 Building AI that understands, reasons, and delivers ║
║ real-world impact 🚀” ║
║ ║
║ ║
╚══════════════════════════════════════════════════════════════════════════════╝