Distinguished AI/ML Engineer specializing in production-grade Large Language Model systems, enterprise AI infrastructure, and scalable cloud architectures. Currently driving AI innovation at Analytiverse, where I architect and deploy mission-critical LLM evaluation frameworks, optimize agentic AI workflows on GCP, and build robust MLOps pipelines that serve thousands of users.
Key Differentiators:
- 🎯 Production AI Systems: Deployed LLM evaluation pipelines achieving 80%+ accuracy validation in production environments
- ⚡ Cloud Infrastructure: Managed GCP VM infrastructure and Docker orchestration for enterprise AI workflows
- 🧠 Full-Stack AI Development: End-to-end AI application development from model training to production deployment
- 🏗️ DevOps Excellence: Built CI/CD pipelines reducing deployment time by 60% using Jenkins, Docker, and Kubernetes
- 📊 Impact-Driven: BS Computer Science, FAST NUCES (CGPA: 3.16) • Stanford/DeepLearning.AI Certified
Jun 2025 - Present | Remote
Leading the development and deployment of enterprise-scale AI systems with focus on LLM evaluation and agentic workflows:
- Infrastructure & Operations: Architected and maintained Google AI workflow infrastructure on GCP, managing VM instances, Docker containers, and automated deployment pipelines for production ML systems
- LLM Evaluation Systems: Engineered Python-based evaluation frameworks for Large Language Models, implementing rigorous testing protocols that achieved 80%+ accuracy validation across diverse use cases
- Agentic AI Optimization: Enhanced and optimized Colab notebooks for training sophisticated Agentic AI pipelines, improving model performance and reducing training time by implementing efficient data preprocessing strategies
- Data Engineering: Developed and deployed LLM-powered data transformation pipelines, automating complex ETL processes and enabling seamless integration with downstream analytics systems
- Impact: Accelerated AI development cycles by 40% through infrastructure automation and streamlined evaluation workflows
Tech Stack: Python, GCP, Docker, LangChain, Jupyter, Git, Linux
MERN Stack • TensorFlow • Docker • Hugging Face Transformers • Cloud Deployment
Enterprise-grade AI platform revolutionizing support for neurodivergent students through intelligent, adaptive assessments.
Technical Highlights:
- Architected scalable MERN stack application with microservices architecture
- Developed custom CNN achieving 92% accuracy for handwriting pattern recognition (dyslexia/dysgraphia detection)
- Implemented JWT-based authentication and role-based access control (RBAC) for multi-tenant security
- Containerized entire stack with Docker for consistent deployment across environments
- Integrated Hugging Face transformers for natural language processing of educational content
Impact: Enables personalized learning pathways for neurodivergent students with 89% user satisfaction rate
LangChain • Faiss • MIMIC-IV Dataset • Transformer Models • Streamlit
Production-ready Retrieval-Augmented Generation system leveraging enterprise medical datasets for clinical decision support.
Technical Architecture:
- Built semantic search engine using Faiss vector database with 50K+ indexed medical records
- Implemented RAG pipeline with LangChain orchestrating Flan-T5 and BART transformer models
- Engineered clinical note summarization achieving 85% Rouge-L score on MIMIC-IV validation set
- Deployed interactive Streamlit interface with real-time query processing (<2s latency)
- Optimized embedding generation and retrieval for production-scale performance
Impact: Reduces clinical documentation review time by 70% while maintaining diagnostic accuracy
Jenkins • Docker • Kubernetes • GitHub Actions • SonarQube • Terraform
Production-grade DevOps pipeline demonstrating industry best practices for automated software delivery.
Pipeline Architecture:
- Orchestrated multi-stage Jenkins pipeline with automated build, test, security scan, and deployment phases
- Containerized Maven application with Docker multi-stage builds (reduced image size by 65%)
- Implemented Kubernetes deployment with auto-scaling, health checks, and rolling updates
- Integrated SonarQube for automated code quality gates (85%+ coverage requirement)
- Configured GitHub Actions webhooks for event-driven CI/CD triggering
Impact: Achieved 60% faster deployment cycles with zero-downtime releases
React • Django REST • Google Gemini AI • PostgreSQL • Vercel • Render
AI-powered conversational interface providing intelligent insights from professional documents.
System Design:
- Built RESTful API with Django handling 1000+ concurrent requests
- Integrated Google Gemini AI for context-aware conversational responses
- Implemented JWT authentication with refresh token mechanism for secure sessions
- Designed PostgreSQL schema optimizing complex query performance (sub-100ms response time)
- Deployed frontend on Vercel with Render backend achieving 99.9% uptime
Impact: Streamlines candidate screening process with 80% time reduction for recruiters
Production ML: TensorFlow • PyTorch • Scikit-learn • Hugging Face Transformers
LLM Systems: OpenAI API • LangChain • RAG Architectures • Prompt Engineering
NLP: Transformer Models • Text Generation • Semantic Search • Embeddings
Computer Vision: CNNs • Image Classification • Object Detection • OpenCV
MLOps: Model Versioning • A/B Testing • Performance Monitoring
Data Science: Pandas • NumPy • Matplotlib • Statistical Analysis
Frameworks: FastAPI • Django • Flask • Express.js • Node.js
APIs: RESTful Design • GraphQL • Microservices • API Gateway
Authentication: JWT • OAuth 2.0 • RBAC • Session Management
Modern Stack: React.js • Next.js • TypeScript • Redux • Context API
Styling: Tailwind CSS • Material-UI • Styled Components
State Management: Redux Toolkit • React Query • Zustand
Cloud Platforms: Google Cloud Platform (GCP) • AWS • Firebase
Containerization: Docker • Docker Compose • Kubernetes • Helm
CI/CD: Jenkins • GitHub Actions • GitLab CI • ArgoCD
Infrastructure: Terraform • Ansible • Nginx • Load Balancing
Monitoring: Prometheus • Grafana • CloudWatch
NoSQL: MongoDB • Redis • Firestore
SQL: PostgreSQL • MySQL • SQLite
Vector Databases: Faiss • Pinecone • Weaviate
Expert: Python • JavaScript/TypeScript
Proficient: C++ • SQL • Bash/Shell Scripting
🏆 Supervised Machine Learning: Regression and Classification
Stanford University / DeepLearning.AI
🏆 Advanced Learning Algorithms
Stanford University / DeepLearning.AI
🏆 Microsoft Ambassador Challenge: Python Exploration
Microsoft Learn Student Ambassadors Program
|
|
|
|
🎯 Production AI Systems: Deployed LLM evaluation achieving 80%+ accuracy
⚡ Cloud Infrastructure: Managed GCP enterprise AI workflow infrastructure
🔧 DevOps Excellence: Reduced deployment time by 60% with CI/CD automation
🧠 Model Performance: Achieved 92% accuracy in CNN-based diagnostics
📊 System Reliability: Maintained 99.9% uptime for production applications
🚀 Development Velocity: Accelerated AI development cycles by 40%
As an AI/ML Engineer with proven experience in production environments, I combine deep technical expertise with practical problem-solving skills. My experience spans the entire ML lifecycle—from research and prototyping to production deployment and monitoring. I'm particularly passionate about:
- Building Scalable AI Systems: Architecting LLM-powered applications that serve real-world users with reliability and performance
- Infrastructure Excellence: Creating robust cloud-native infrastructures that support rapid iteration and deployment
- Cross-Functional Impact: Collaborating with product, design, and business teams to translate requirements into technical solutions
- Continuous Innovation: Staying at the forefront of AI/ML advancements and applying cutting-edge techniques to solve complex problems
I thrive in fast-paced environments where I can contribute to meaningful products that positively impact users' lives.
I'm always excited to discuss AI/ML innovations, collaborate on challenging projects, or explore new opportunities with forward-thinking teams.
