I build production-ready LLM systems and agentic AI pipelines that automate complex workflows. Top Rated on Upwork | 20+ projects in multi-agent AI, generative models & data engineering with PyTorch. Clients come to me when they need AI systems that actually ship — not prototypes. Whether it's a multi-agent orchestration layer, a custom RAG pipeline, a diffusion model for audio/image generation, or a data engineering workflow at scale, I handle the full cycle from architecture to deployment. What I work on: → Agentic AI & Multi-Agent Systems (LangChain, LangGraph, Groq, tool-use agents) → LLM Integration & RAG (retrieval pipelines, fine-tuning, prompt engineering) → Generative AI — Audio & Image (diffusion models, voice synthesis, latent space modeling) → ML Model Development (PyTorch, TensorFlow, classification, NLP, CV) → Data Engineering & Pipelines (PySpark, AWS SageMaker, ETL, 100GB+ datasets) Recent work includes a 7-layer multi-agent data processing engine, a latent diffusion model for synthetic medical audio generation (reduced FAD from 18.82 → 14.71), and a natural language chatbot interface for Grafana dashboards. I communicate clearly, deliver on time, and document everything. I don't disappear mid-project and I don't overpromise scope. If something's not feasible, I'll tell you upfront. If you're building something serious in AI — let's talk. Send me a message and I'll usually reply within a few hours.

Need a Salesforce expert who can combine the power of AI with a scalable CRM? You're in the right place. I'm a Salesforce AI Developer with expertise in building intelligent, automated, and user-friendly Salesforce solutions that help businesses save time, improve customer experiences, and grow faster. Whether you need to customize Salesforce, implement Agentforce, integrate Einstein AI, or connect your CRM with modern AI models like OpenAI, Claude, or Llama, I can help you build a solution that delivers real business value. What I can help you with: ✅ Agentforce implementation and custom AI agents ✅ Einstein AI & Prompt Builder ✅ Salesforce development with Apex & Lightning Web Components (LWC) ✅ Flow Builder and CRM automation ✅ Sales Cloud, Service Cloud & Experience Cloud ✅ Data Cloud implementation and customer insights ✅ AI chatbots and conversational experiences ✅ OpenAI, Claude & Llama integrations ✅ LangChain & RAG-powered AI assistants ✅ Python, FastAPI, REST APIs & MuleSoft integrations ✅ Custom Salesforce apps and third-party integrations I don't just build features—I build solutions that simplify operations, automate repetitive tasks, and help your team work more efficiently. My goal is to deliver clean, scalable, and maintainable Salesforce applications that continue to add value as your business grows. I believe clear communication, reliable delivery, and understanding your business goals are just as important as writing great code. You'll always know where your project stands, and I'll work closely with you to ensure the final solution meets your expectations. If you're looking for a dependable Salesforce AI developer who understands both enterprise CRM and the latest AI technologies, I'd love to hear about your project. Let's build something amazing together. Core Skills: Salesforce • Agentforce • Einstein AI • Data Cloud • Apex • Lightning Web Components (LWC) • Flow Builder • Sales Cloud • Service Cloud • Experience Cloud • OpenAI • Claude • Llama • LangChain • RAG • AI Agents • AI Chatbots • CRM Automation • Python • FastAPI • REST API • SOAP API • MuleSoft

I help businesses build practical AI/ML systems, evaluate model performance, and create reliable Python-based data pipelines. My work focuses on helping clients move from messy data, manual processes, or early AI ideas to clean, measurable, and production-ready systems. Whether you need a machine learning model, data pipeline, forecasting workflow, model evaluation process, or Python-based automation, I can help you design and build a solution that is clear, reliable, and useful. I can help with: * Machine learning model development and evaluation * AI/LLM workflow testing and response evaluation * Data cleaning, transformation, and analysis * Python-based automation and backend workflows * Data pipelines for structured and unstructured data * Forecasting and prediction models * Classification, clustering, and anomaly detection * Dashboard-ready datasets and reporting workflows * API integration and model output processing I focus on practical implementation, not just technical experiments. My goal is to help you build systems that are accurate, easy to understand, maintainable, and useful for real decision-making. I work with Python, SQL, R, machine learning libraries, data visualization tools, and cloud-based data workflows. I can also support projects involving model monitoring, prompt testing, evaluation metrics, data validation, and process automation. If you are looking for someone who can connect AI/ML, data engineering, model evaluation, and Python development into one practical solution, I would be happy to help.

I build production-ready Computer Vision, Generative AI, and Data Science systems that solve real business problems, from object detection pipelines and LLM-powered RAG applications to intelligent AI agents that automate complex workflows. Top Rated AI/ML Engineer with 5+ years delivering end-to-end solutions using PyTorch, YOLO, LangChain, OpenAI API, and Anthropic API. I've shipped defect detection models for manufacturing floors, built RAG chatbots that sit on top of company knowledge bases, designed fraud detection pipelines for fintech clients, and deployed AI agents that replaced hours of manual work. Every project I take on goes from problem to working, deployed system, not just a Jupyter notebook. I communicate clearly, deliver on time, and care about your outcome as much as the tech behind it. 👁️ Computer Vision: • Object Detection & Tracking (YOLOv8, YOLOv9, YOLOv11, SSD, Faster R-CNN, DETR) • Image Segmentation (Semantic, Instance, Panoptic, SAM, SAM 2) • OCR & Intelligent Document Processing (TesseractOCR, EasyOCR, PaddleOCR, DocTR) • Face Recognition, Facial Attribute Analysis & Emotion Detection • Vision Language Models (CLIP, BLIP, Florence, GPT-4V, Gemini Vision) • Image Enhancement, Super-Resolution & Visual Search • Video Analysis & Real-time Object Tracking (DeepSORT, ByteTrack, BoT-SORT) • AI Image Generation & Editing (Stable Diffusion, ControlNet, Inpainting) • CNNs, Vision Transformers (ViT), EfficientNet & Transfer Learning • Visual Inspection & Defect Detection for Manufacturing & Quality Control • Medical Image Analysis & Document Parsing • Multimodal AI Systems (combining vision, text & audio) 🤖 Generative AI & LLMs: • RAG (Retrieval Augmented Generation) Pipelines & Knowledge Bases • LLM Fine-tuning (LoRA, QLoRA, PEFT, RLHF, DPO) • Prompt Engineering & Optimization • OpenAI API (GPT-4, GPT-4o, GPT-5), Anthropic API (Claude), Google Gemini • Open-source LLMs (Llama 3, Mistral, Qwen, Phi, DeepSeek, Gemma) via Hugging Face Transformers • Custom AI Chatbot Development & Virtual Assistants • LangChain, LlamaIndex, Haystack • AI Integration into Existing Systems & Workflows • Speech-to-Text (OpenAI Whisper) & Text-to-Speech (TTS, ElevenLabs) • Embedding Models & Vector Search • Document AI: Extraction, Parsing & Intelligent Processing 📊 Data Science & Machine Learning: • Exploratory Data Analysis (EDA) & Feature Engineering • Predictive Modeling, Forecasting & Predictive Analytics • Classical ML (XGBoost, LightGBM, CatBoost, Random Forest, SVM, KNN) • Time Series Analysis, Forecasting & Anomaly Detection • Classification, Regression & Clustering • Model Evaluation, Selection & Hyperparameter Tuning • Data Preprocessing, Cleaning & Wrangling • Data Visualization & Dashboards (Matplotlib, Seaborn, Plotly) • Fraud Detection & Risk Analysis • Recommendation Systems 🔄 AI Agents & Automation: • Agentic AI Workflows (LangGraph, CrewAI, AutoGen, Agno) • Multi-Agent Systems & Tool-Use Agents • Model Context Protocol (MCP) Integrations • AI-powered Workflow Automation (n8n, Make, Zapier) • End-to-end Pipeline Orchestration & AI Integration • Autonomous Task Execution & Decision-Making Systems • Voice AI Agents (VAPI, Bland AI) ✅ Tech Stack: ➼ Languages: Python ➼ ML/DL Frameworks: PyTorch, TensorFlow, Keras, Scikit-Learn, Hugging Face Transformers ➼ Computer Vision: OpenCV, Ultralytics (YOLO), PIL, TesseractOCR, EasyOCR, PaddleOCR, Roboflow ➼ GenAI / LLM: LangChain, LlamaIndex, LangGraph, OpenAI API, Anthropic API, Hugging Face ➼ Data & Analytics: Pandas, NumPy, Matplotlib, Seaborn, Plotly, Scipy ➼ API & Deployment: Flask, FastAPI, Docker, Streamlit, Gradio ➼ Cloud: AWS (SageMaker, EC2, S3, Lambda), Azure, GCP ➼ Databases: Pinecone, ChromaDB, Faiss, Weaviate, PostgreSQL, MongoDB ➼ MLOps: MLflow, Weights & Biases, Model Versioning & Monitoring ➼ IDE: VS Code, PyCharm, Jupyter Notebook, Google Colab 🚀 Why work with me: Production-Focused: I don't just prototype, I ship deployed, working systems that integrate with your workflow and deliver measurable value. Results-Driven: Every project starts with your business goal. Whether it's automating visual inspection, building a smart chatbot, detecting fraud, or extracting insights from documents, the model is a means to your outcome. Modern & Current: The AI field moves fast and so do I. I stay on top of what actually works, LLMs, RAG, AI agents, vision-language models, multimodal AI, so your solution uses cutting-edge approaches, not outdated ones. Clear Communication: Top Rated with a strong Job Success track record. I communicate clearly, meet deadlines, and treat every project as a real partnership. 🤝 Let's work together to push the boundaries of what's possible!

With 4+ years in AI, I bridge the gap between advanced research and production engineering. I don't just train models; I build the scalable infrastructure to serve them. My expertise takes custom neural networks from mathematical theory to fully deployed, production-grade APIs on Kubernetes clusters. 🛠️ Core Technical Stack 1. Generative AI & Agents Tech: LLMs, AI Agents, RAG, LiveKit, TTS, STT, LangGraph, MCP, n8n workflows. Memory & Context: mem0 (Memory Management), RAG pipeline optimization. 2. Deep Learning & Neural Networks Core: PyTorch, Stable Diffusion, Transformer, 3D U-Net, IP-Adapter, ControlNet, ArcFace. 3. Backend API Development & Real-Time Streaming Frameworks: Expert in FastAPI (Async/High-concurrency) and Flask for serving ML models. Protocols: RESTful APIs, WebSockets, gRPC, and Swagger/OpenAPI documentation. Streaming: LiveKit, WebRTC, Socket.io for low-latency interactive AI. 4. MLOps, DevOps & Big Data CI/CD & Monitoring: GitHub Actions, Sentry (Error Monitoring), Automated Testing Pipelines. Infrastructure: Docker, Kubernetes (Scalable Clusters). Data Engineering: Kafka, Debezium, PySpark for real-time data streaming. HPC: Distributed training (Multi-node/Multi-GPU) on A100 & H100 clusters. 📂 Project Showcase 🤖 Intelligent Voice Agent & RAG System Role: Led the upgrade of a Voice Agent (v0.x to v1.x), serving the RAG pipeline via optimized FastAPI endpoints. Agentic Workflow: Implemented long-term memory using mem0 and integrated n8n workflows via an MCP server. Ops: Deployed on Kubernetes with GitHub Actions for CI/CD and Sentry for real-time error tracking. 🎥 Real-Time Talking Avatar Role: Integrated LiveKit (WebRTC) with Wav2Lip for a live-streaming avatar solution. Performance: Achieved sub-200ms latency on GPU clusters using optimized socket streaming. Impact: Reduced deployment costs by 50% through rigorous model pruning, quantization, and fine-tuning. 🚀 Stable Video Diffusion & HPC Training Role: Developed distributed training code for complex architectures (3D U-Net, IP-Adapter, ControlNet) using DensePose and 3D pose datasets. Infrastructure: Trained on 4x A100 (single node) and 2x H100 (multi-node) clusters. Result: Achieved 40% faster convergence through multi-node optimization compared to single-GPU training. 🗳️ Election Prediction System (Oman Shura Election) Role: Engineered a real-time election analysis pipeline using Debezium, Kafka, and PySpark. Modeling: Deployed Transformer-based models on 4x A10 GPUs to forecast polling percentages for 63 regions. Visualization: Created interactive dashboards visualizing 6 years of historical voting data. 💬 Speech-to-Text (Whisper ASR) Role: Trained and deployed OpenAI’s Whisper model using the Libri-speech dataset. Impact: Created a high-availability API pipeline capable of handling diverse audio inputs.

⭕Upwork Top 10% Freelancer⭕ ⭕100% Customer Satisfaction⭕ I help businesses implement Generative AI to automate workflows, build intelligent chatbots, and integrate AI into real products. My work focuses on LLMs, RAG architectures, AI agents, and automation pipelines — designed for production use, not experiments. What I Build LLM & RAG systems for internal tools and customer-facing applications AI chatbots & assistants powered by GPT and open-source models AI automation for operations, data workflows, and decision support API-based AI services using Python, FastAPI, and Docker Why Clients Choose Me Clear understanding of business use cases Clean, scalable AI system design Fast execution with practical results Strong communication from start to delivery If you’re planning to adopt GenAI, build an AI chatbot, or automate processes using LLMs, send an invite and let’s talk.

🚀 AI-Driven Energy Forecasting | Data Science | Machine Learning Are you looking to optimize energy operations with AI, or need accurate demand forecasting? I’m a Data Scientist with a Master’s degree and over 4 years of experience in applying Machine Learning, Time Series, and Predictive Modeling to energy systems and data-intensive problems. ✅ My expertise includes: 📊 Time Series Forecasting – energy demand, pricing, weather, streamflow 🔍 Predictive Modeling – regression, classification, model tuning ⚡ AI in Energy Systems – load prediction, energy trading optimization 📈 Data Analytics & Visualization – insights that drive real-world decisions 🧠 Deep Learning & Reinforcement Learning – for autonomous systems and intelligent control 🛠️ Project Design & Consulting – roadmap creation for scalable AI solutions I’ve worked on projects involving: Electricity price and demand forecasting for utilities ML-based streamflow prediction Optimization of energy portfolios using RL Data visualization dashboards using Python (Plotly, Dash, etc.) 🔧 Tools/Tech: Python, Scikit-learn, TensorFlow, Keras, pandas, NumPy, XGBoost, Prophet, SQL, Power BI Let’s discuss how I can bring real intelligence to your energy or analytics challenges.

👋 Expert Machine Learning, Generative AI Engineer and Full Stack Web Development. I am passionate about solving complex problems and making a positive impact. I bring experience across various projects, specialising in Machine Learning, Generative AI, and Cloud solutions. My expertise includes leveraging tools and frameworks such as Pandas, Matplotlib, Seaborn, Scikit-Learn, OpenCV, TensorFlow, PyTorch, Hugging Face Transformers, LangChain, ChatGPT, Gemini, Llama, Cohere, Pinecone, LlamaIndex, and more to build innovative solutions. I am an AWS Certified Generative AI Developer Professional, AWS Certified Machine Learning Engineer Associate, AWS Certified AI Practitioner, Google Cloud Certified Associate Cloud Engineer, Google Cloud Certified Generative AI Leader, a Databricks Certified Generative AI Engineer Associate, and an Oracle Cloud Infrastructure 2024 Generative AI Certified Professional. I am skilled in data analysis, predictive modelling, sentiment analysis, classification, regression, clustering, and object detection. My strong foundation in Python, JavaScript, and SQL, coupled with experience developing REST APIs, enables me to create robust solutions. I am also well-versed in cloud computing, with expertise in deploying machine learning models on both Google Cloud and AWS. 🚩AREA OF EXPERTISE ----------------------------------- ✔️ LLM Fine-tuning & Deployment ✔️ Generative AI Applications ✔️ Retrieval-Augmented Generation (RAG) ✔️ Machine Learning (ML) and Deep Learning(DL) ✔️ Data Analysis and Visualisation ✔️ Natural Language Processing(NLP) ✔️ Time series forecasting, Anomaly detection ✔️ AI Applications building using open-source models and Hugging Face tools ✔️ GCP & AWS AI Services ✔️ API Development 🚩TECHNICAL SKILLS -------------------------------------------------------- ✔️ Python, JavaScript, SQL ✔️ LangChain | LangGraph | LlamaIndex | Autogen | Swarm | CrewAI | OpenAI GPT-4o | Claude | Gemini | Llama 3 ✔️ Pinecone | Qdrant | Chroma | FAISS ✔️ Numpy, Pandas, Jupyter Notebook, Matplotlib, Seaborn, Plotly ✔️ SciKit-Learn, NLTK, BeautifulSoup, Statsmodel ✔️ TensorFlow, Keras, PyTorch, PyTorch Lightning ✔️ OpenCV, Scikit-Image, Pillow, Tesseract ✔️ DNN, CNN, RNN/LSTM, GAN ✔️ Hugging Face Transformers, ✔️ FastAPI, Flask, Streamlit I believe clear communication is key to success, and I prioritise understanding my clients' needs and vision. I'm excited to apply my skills to new challenges and am confident in making valuable contributions to any team. Thank you for considering my profile, and I look forward to the opportunity to work with you soon.

Expert-Vetted Top 1% AI Engineer. 11+ years building production systems trusted by P&G, Edwards Lifesciences, Canva, and Shotdeck across 80+ deployments. I build autonomous agent architectures and vision systems that don't break in production. If your current AI setup is a fragile chain of API wrappers draining your token or compute budget, I engineer the production-grade recovery. By integrating real-time computer vision pipelines and enterprise knowledge bases to advanced LLM orchestrators, I replace unstable loops with systems that run cheaper, break less, and scale without the maintenance overhead. The architectural principle across every engagement: isolate the binding constraint before any model decision — HIPAA compliance in clinical pipelines, sub-second retrieval across 3M+ cinematic assets, compute efficiency at 2M+ API calls/year, real-time inference at the edge. I own the full stack from data strategy through high-reliability maintenance. WHAT I BUILD • Agentic & Hybrid RAG Architecture: For retrieval systems that don't just find — they self-correct. Stateful loops in LangGraph and LlamaIndex with Corrective RAG (CRAG), query rewriting, cross-encoder reranking, and GraphRAG. Proven at scale: Shotdeck's 3M+ cinematic asset library at sub-second latency. • Claude Agent SDK & Context Engineering: Agents that don't bloat, stall, or hallucinate tools. I deploy Context Extractors to map and feed minimal, structured JSON facts into isolated subagent context windows — cutting token overhead without cutting capability. Delivered 40% reduction in token costs for a financial enterprise. Biscuit AI: coordinator/subagent state machine from prototype to production in 4 weeks. • Claude Code & Workspace Production: Hierarchical CLAUDE.md configuration for autonomous developer environments and reusable tools built to the open Agent Skills standard — so your agentic setup scales beyond one engineer. • Enterprise Guardrails & MCP Servers: Agents that touch real data need to be hardened, not just functional. Custom MCP servers in Python with deterministic lifecycle hooks (PreToolUse/PostToolUse), validation-retry loops, and structured error handling via isError flags. Transport-agnostic (stdio, SSE, HTTP) — built for HIPAA-compliant pipelines, fintech, and any environment where a mistake has consequences. • Computer Vision & Multimodal RAG: When your cameras and sensors need to talk to your LLMs. Real-time object detection and segmentation (PyTorch/YOLO) bridged to text via hybrid RAG pipelines. Built Shelfr's retail vision platform across 200+ FMCG brands including P&G (2025 External Business Partner Excellence Award). 85%+ PHI detection in HIPAA-compliant clinical imaging for Edwards Lifesciences. WHAT I USE TO BUILD • LLMs & Agent Frameworks: Claude, GPT-4o, Llama 3+, DeepSeek — Claude Agent SDK, LangGraph, LangChain, LlamaIndex, CrewAI, Pydantic v2 • RAG & Retrieval: pgvector, HNSW, Qdrant, Vespa, Pinecone, Weaviate, ColPali, ColBERT, Corrective RAG (CRAG), cross-encoder reranking • Computer Vision & Healthcare: YOLO v5–v11, YOLO-World, Grounding DINO, SAM 2, OpenCV, ViT, Swin Transformers — MONAI, nnU-Net, MedSAM, DICOM • Infrastructure & Deployment: MCP (Client/Server), Claude Code, Modal, AWS, GCP, FastAPI, Docker Most AI projects fail somewhere between the demo and production. I've closed that gap 80+ times. Click "Invite to Job" or "Message" and describe your bottleneck — I respond within 24 hours and have a scoped production path to you within 48.

I bring over 2 years of hands-on experience at the Singapore University of Technology and Design, where I’ve built real-world intelligent systems using Deep Learning, Generative AI, and Reinforcement Learning — and I’m just getting started. I’m a Computer Science graduate, and I’ve spent over 5 years personally learning, exploring, and applying AI across different fields. From tracking athletes and guiding robots to reading license plates and monitoring construction site progress, I specialize in turning creative ideas into practical, and high-impact ML solutions. Accomplishments: ⭐️ IBM Hackathon Winner – Built a real-time deep learning system for cricket pose estimation. ⭐️ ANPR | FRS for KAVACH Hackathon (Top 5) – Developed YOLOv8 based multilingual license plate + OCR and passenger detection solution. ⭐️ 360° Construction site Monitoring – Deployed a panoramic image segmentation system for tracking and analyzing construction site progress. ⭐️ Generative RL for Robotics – Created multi-agent systems that enable helps robots figure out how to assemble things @SUTD. ⭐️ NLP for EdTech – Built transformer-based machine translation solution and Chatbot for a global learning platform. Core Skills & Tools: ✔Machine Learning with Pytorch, Tensorflow, Scikit Learn, Unity 3D (ML - Agents), Unreal Engine 5.0 ✔NLP with Transformer models, RNN, Attention models and Text data preprocessing with Spacy. ✔Image Segmentation with U-Net, PIX2PIX GAN, Spherical U-Net (360 degree image segmentation), 3D Space Segmentation (with 3DGS, NeRF, GARField etc). ✔Object Detection and Image Classification with YOLO, Efficient Nets, OneShot Learning etc. ✔Generative Modeling with RL (Deep Q Learning, PPO, DDPG, Multi-Agent RL, Unity ML-Agents) ✔Additional Skill - Animation and Designing with blender and UE My research expertise ensures timely delivery and high-quality results. I believe in strong communication, idea-sharing, and building solutions that actually make a difference. Let’s bring your AI vision to life.