Senior Machine Learning engineer with over 10 years of extensive experience in Speech, Image, Text and Video processing applications. 💥Post-doc in Speech and Language processing focusing Automatic Speech Recognition. 💥PhD in Multimodal (audio-visual) speaker diarization including facial recognition, speaker identification, audio-visual synchronization. Experience in: 🔸Voice agents (LiveKit, VAPI, n8n) 🔸Text-to-speech models (StyleTTS2, OrpheusTTS, etc.) 🔸Chatbots (LangChain, LangGraph, CrewAI etc.) 🔸Automatic Speech Recognition (wav2vec2, Whisper etc.) 🔸Audio quality estimation (PESQ, STOI etc.) 🔸Facial recognition 🔸Speech Activity Detection (SAD) 🔸Audio-Visual Speaker Diarization 🔸Multiview panoramic imaging 🔸Image denoising and many more... Frameworks/ Tools/ Platform: 🔸PyTroch, Tensorflow 🔸Web GUI (Gradio, Dash/Plotly, Streamlit) 🔸Grid computing (Slurm, SGE) 🔸Multi-GPU training. 🔸Linux, Shell scripting 🔸AWS, Runpod 🔸SQL and BigQuery I always look to build a long term relationship with my clients. Looking forward to hearing from you. Thank you.

I architect AI systems that actually work in production from LLM apps to real-time decision engines. If you need more than a prototype, I can help you design and scale it. As a TopTal certified AI architect (top 3% global talent) with 8+ years of experience, I specialize in designing 𝐋𝐋𝐌-𝐩𝐨𝐰𝐞𝐫𝐞𝐝 𝐚𝐩𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧𝐬, 𝐑𝐀𝐆 𝐩𝐢𝐩𝐞𝐥𝐢𝐧𝐞𝐬, and 𝐢𝐧𝐭𝐞𝐥𝐥𝐢𝐠𝐞𝐧𝐭 𝐚𝐠𝐞𝐧𝐭𝐬 used in fintech, cybersecurity, and enterprise AI decision systems. 𝐌𝐨𝐬𝐭 𝐀𝐈 𝐩𝐫𝐨𝐣𝐞𝐜𝐭𝐬 𝐟𝐚𝐢𝐥 𝐛𝐞𝐜𝐚𝐮𝐬𝐞 𝐭𝐡𝐞𝐲 𝐬𝐭𝐨𝐩 𝐚𝐭 𝐝𝐞𝐦𝐨𝐬. 𝐈 𝐟𝐨𝐜𝐮𝐬 𝐨𝐧: - Turning models into scalable, reliable systems - Improving accuracy, latency, and real-world performance - Designing end-to-end AI pipelines, not isolated experiments 𝐖𝐡𝐚𝐭 𝐈 𝐂𝐚𝐧 𝐁𝐮𝐢𝐥𝐝 𝐅𝐨𝐫 𝐘𝐨𝐮: - LLM Applications (GPT, OpenAI, Claude, etc.) - RAG Pipelines (LangChain, vector DBs, semantic search) - AI Agents (multi-step reasoning, automation workflows) - Conversational AI (RASA, Dialogflow, custom NLP systems) - Predictive Models (time series, anomaly detection, trading systems) - AI for Cybersecurity (threat detection, phishing detection) 𝐑𝐞𝐚𝐥 𝐈𝐦𝐩𝐚𝐜𝐭 𝐈’𝐯𝐞 𝐃𝐞𝐥𝐢𝐯𝐞𝐫𝐞𝐝: - Built AI systems for cyber threat analysis and response automation - Developed algorithmic trading models using time series forecasting - Designed context-aware conversational AI systems - Improved model performance through feature engineering & optimization - Reduced false positives in ML systems with behavior-based scoring 𝐓𝐞𝐜𝐡 𝐒𝐭𝐚𝐜𝐤: - Python • PyTorch • TensorFlow • NLP (BERT, SpaCy) • Node - LangChain • RAG • FastAPI • Kafka • Redis - AWS • GCP • Kubernetes • Microservices 𝐖𝐡𝐲 𝐂𝐥𝐢𝐞𝐧𝐭𝐬 𝐖𝐨𝐫𝐤 𝐖𝐢𝐭𝐡 𝐌𝐞: - I understand both AI + production systems - I focus on business outcomes, not just models - I can take your idea from prototype → scalable system If you're building something where accuracy, reliability, and real-world impact matter, 𝐥𝐞𝐭'𝐬 𝐭𝐚𝐥𝐤.

Experienced in building scalable real-time video intelligence systems — from traffic analytics to sports performance tracking, OCR, Speech Processing, and LLMs. With 5 years of expertise in real-time video analytics, document automation, and AI-driven insights, I leverage top technologies like Pytorch, TensorFlow, Deepstream, OpenCV, DeepSpeech, and Hugging Face to deliver scalable, intelligent systems. Let’s transform your vision into reality! 🚀 🔧 Tech Stack : 💻 Computer Vision and Video Analytics 🔹 OpenCV 🔹 TensorFlow 🔹 PyTorch 🔹 YOLO (You Only Look Once) 🔹 MMPose (Pose Estimation) 🔹 GStreamer (Video Processing) 📄 OCR and Document Processing 🔹 Tesseract OCR 🔹 EasyOCR 🔹 Pytesseract 🔹 Google Cloud Vision API 🔹 AWS Textract 🤖 RAG and LLMs (Large Language Models) 🔹 OpenAI GPT-3/4 🔹 Hugging Face Transformers 🔹 LangChain 🔹 Pinecone (Vector Database) 🔹 LLamaIndex 🔹 Ray (Distributed Computing for LLMs) 🎤 Speech Processing and Speech-to-Text 🔹 Google Speech-to-Text 🔹 Amazon Transcribe 🔹 Microsoft Azure Speech Service 🔹 DeepSpeech (Mozilla) 🔹 Coqui 🔹 Whisper (OpenAI) ⚙️ Deep Learning & Hardware Acceleration 🔹 CUDA (GPU Acceleration) 🔹 TensorRT 🔹 NVIDIA DeepStream SDK 🔹 OpenVINO 🔹 Jetson Nano (Edge Computing) 🔹 EdgeTPU 🌐 Cloud, Deployment, and DevOps 🔹 Docker 🔹 Kubernetes 🔹 AWS S3 🔹 GCP AI Platform 🔹 Jenkins 🛠️ Previous Projects : 1. AI-Powered Smart City Traffic Management System 🚦🚘 2. Smart Factory Monitoring and Safety System 🏭🚧 3. Voice-Activated Medical Transcription System 🩺📝 4. Multimodal Document Understanding and Automation 📄🤖 5. Personalized Virtual Assistant for Customer Support 🎙️💬 6. Real-Time Sports Analytics and Player Performance Tracker ⚽📊 7. Smart Home Surveillance and Intruder Detection 🏡🎥 8. AI-Powered Healthcare Data Extraction and Analysis 🏥📈 9. AI-Driven Financial Document Automation 💼📑 10. Real-Time Video Surveillance for Compliance in Factories 🎥🏭 🚀 Let’s Build the Future Together! With my extensive experience in deploying AI-driven solutions across multiple domains, I'm ready to take your projects to the next level. From Computer Vision to LLMs and OCR, I bring a passion for innovative technology and a track record of delivering high-impact solutions. Let’s transform your ideas into reality and drive success together!

Most businesses are sitting on valuable data they never actually use. I help turn that data into predictive models, intelligent systems, and decisions that improve revenue, reduce risk, optimize operations, and uncover new opportunities. From customer churn and demand forecasting to revenue analytics, financial forecasting, anomaly detection, and AI automation, I build data science solutions that solve real business problems. I focus on outcomes, not just models. Every solution is designed to fit into your existing workflow and deliver insights your team can act on immediately. 100% Job Success Score. Top Rated on Upwork. 5-star reviews across every completed engagement. If your business is generating data, there's probably an opportunity hidden in it. Let's find it.

𝗦𝗲𝗻𝗶𝗼𝗿 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 & 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗼𝗻 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿 — 𝗧𝗼𝗽 𝗥𝗮𝘁𝗲𝗱 | 𝟭𝟬𝟬% 𝗝𝗦𝗦 | $𝟮𝟬𝗞+ 𝗲𝗮𝗿𝗻𝗲𝗱 I build production-grade AI agents and n8n automations that cut manual back-office work by 70–90% — production systems, not demos. Top Rated on Upwork with 22 successful builds spanning agentic workflows, RAG over private data, and Claude / GPT-4 integrations. If you're looking to: • Automate multi-step business workflows with AI agents (not basic chatbots) • Build RAG systems over your internal docs, PDFs, and databases • Wire LLMs into HubSpot, Airtable , Social Networking Apps or custom CRMs via n8n • Integrate Claude / GPT-4 / open-source LLMs into your SaaS or internal tools — I'll help you scope, design, and ship a system that runs in production from day one. 🚀 What I build: • Agentic workflows with LangGraph, CrewAI, and Claude / OpenAI tool-use — multi-step decisions, not Q&A • End-to-end automations in n8n / Make / Zapier wired into HubSpot, Airtable, QuickBooks, Notion • RAG systems over 10K–500K docs using Pinecone, Weaviate, or pgvector — production-grade retrieval • Custom LLM solutions — fine-tuning (LoRA / QLoRA), prompt pipelines, evals, inference optimization • Computer Vision when projects need it — SAM, YOLO, custom CNNs (Coursera Deep Learning Specialization, NUST background) 📊 Selected client work: ▶ Agentic Claude Workflow — SaaS Business Automation ⭐⭐⭐⭐⭐ Designed and shipped a multi-agent system in LangGraph + Claude tool-use that auto-categorizes inbound requests, drafts responses, escalates edge cases, and posts to Slack — cutting the client's manual triage by ~80%. Feedback: "He has the kind of energy and quality that is rare to find." Stack: LangGraph · Claude API · Python · Slack · n8n ▶ AI Grading Bot — EdTech Platform • $5K+ contract, 210+ hours, ongoing Built an LLM-powered grading assistant that evaluates student submissions against structured rubrics, returns justified feedback, and integrates with the platform's review queue. RAG over rubrics + exemplar submissions for grading consistency. Stack: Python · OpenAI API · FastAPI · PostgreSQL · pgvector ▶ Healthcare AI — HL7 + DICOM + AWS Pipeline • ongoing Building a cloud-native medical-imaging pipeline integrating HL7 messaging, DICOM image processing, and AWS deployment for a healthcare client. Stack: Python · AWS · DICOM · HL7 · FastAPI · Docker ▶ Imbalanced-Dataset ML Pipeline — Biomedical Research ⭐⭐⭐⭐⭐ • $2.4K, 94 hours Engineered the feature-engineering + statistical-modeling pipeline that outperformed the client's recommended ML baseline. Feedback: "He just outperformed my recommended Machine Learning model with great feature engineering and analytics used. Highly Recommended!!" Stack: Python · scikit-learn · Pandas · Imbalanced-learn · Statistical Methods ▶ Surgical Video Segmentation — Deep Learning ⭐⭐⭐⭐⭐ Trained and fine-tuned a deep-learning segmentation model on surgical video data for a medical research team. Feedback: "Usama delivered excellent work on our surgical video segmentation project. Highly recommended!!" Stack: PyTorch · SAM · OpenCV · Computer Vision Range of recent work: Reinforcement Learning for Energy-Systems Optimization · GAN Networks (5★) · Image-to-SVG Pipeline (5★) · Vision-Language Document Captioning · Real-time Video Behavior Analysis · WhatsApp Bot Automation · Server-side ML/Automation Backends. 🧠 Stack: Python · LangChain · LangGraph · CrewAI · n8n · Make · Zapier · OpenAI API · Anthropic Claude · Pinecone · Weaviate · pgvector · FastAPI · Docker · AWS · GCP · PostgreSQL · PyTorch · TensorFlow · OpenCV · YOLO · SAM 💡 Why clients work with me: • Top Rated, 100% Job Success, $20K+ earned, 22 builds — 5★ across the board where feedback was given • Production systems, not demos — every project ships running code with monitoring, error handling, and a clear handoff • End-to-end ownership: architecture → build → deploy → handoff. You own the code, the keys, the data — always • NUST + Coursera Deep Learning Specialization — real ML foundations, not just LLM-API wiring 📞 Let's talk Send me a message describing the workflow you want automated or the agent you want built. I'll reply within an hour with a 30-minute architecture sketch and an honest "this fits / this doesn't" answer. First 30-min consultation is free.

33+ Successful Projects • 100% Job Success Top Rated 🎯 Computer Vision — YOLOv8/11, Faster R-CNN, U-Net, DeepLabV3+ 📍 Multi-Object Tracking — SORT, DeepSORT, ByteTrack 💬 LLM Applications — RAG, LangChain, Hugging Face, LoRA/QLoRA ⚡ Real-Time AI Deployment — OpenCV, PyTorch, TensorFlow 📈 Scalable Search — FAISS, vector DBs for face & document retrieval 🤖 LLM-Powered Telegram Bots — intelligent assistants & automation Why Work With Me 🟢 25+ successful projects with 100% Job Success (Top Rated) 🟢 Up to 90% automation through AI & workflow optimization 🟢 Scalable, production-grade systems (millions of records, real-time pipelines) 🟢 True end-to-end delivery — strategy → data → model → deployment 🟢 On-time delivery with measurable business impact 🟢 Clear, reliable communication throughout the project 📩 Message me for a free consultation — I’ll help you outline the best technical approach for your project.

AI Engineer specializing in Generative AI, Large Language Models (LLMs), multi-agent systems, machine learning, and computer vision. I help companies design and build 𝗟𝗟𝗠 applications, 𝗥𝗔𝗚 knowledge systems, 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀, 𝗺𝘂𝗹𝘁𝗶-𝗮𝗴𝗲𝗻𝘁 workflows, and production-grade 𝗺𝗮𝗰𝗵𝗶𝗻𝗲 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴 systems using Python and modern AI frameworks. With 24+ years of experience in 𝗰𝘆𝗯𝗲𝗿𝘀𝗲𝗰𝘂𝗿𝗶𝘁𝘆 and deep-tech software engineering, I focus on building AI systems that are 𝘀𝗲𝗰𝘂𝗿𝗲, 𝘀𝗰𝗮𝗹𝗮𝗯𝗹𝗲, and 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆. I currently lead AI engineering department at Apriorit, a software R&D company with 400+ engineers, where we develop advanced AI systems for Cybersecurity, Healthcare, and FinTech. What I Build 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 ↳ Predictive analytics and ML pipelines ↳ Fraud detection and anomaly detection ↳ Recommendation systems ↳ Data processing and feature engineering pipelines 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 / 𝗟𝗟𝗠 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 ↳ 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹-𝗔𝘂𝗴𝗺𝗲𝗻𝘁𝗲𝗱 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 (RAG) knowledge systems ↳ 𝗟𝗟𝗠-𝗽𝗼𝘄𝗲𝗿𝗲𝗱 𝗮𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁𝘀 and enterprise AI 𝗰𝗵𝗮𝘁𝗯𝗼𝘁𝘀 ↳ 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 and 𝗺𝘂𝗹𝘁𝗶-𝗮𝗴𝗲𝗻𝘁 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 for complex workflows ↳ 𝗟𝗟𝗠 𝗳𝗶𝗻𝗲-𝘁𝘂𝗻𝗶𝗻𝗴 and evaluation ↳ Private / 𝗼𝗻-𝗽𝗿𝗲𝗺𝗶𝘀𝗲 𝗟𝗟𝗠 𝗱𝗲𝗽𝗹𝗼𝘆𝗺𝗲𝗻𝘁𝘀 for sensitive environments 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 ↳ OCR and document understanding ↳ Object detection and tracking ↳ Image classification and segmentation ↳ Medical imaging and industrial automation 𝗦𝗲𝗰𝘂𝗿𝗲 𝗔𝗜 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 ↳ Privacy-preserving AI architectures ↳ Adversarial ML defense ↳ AI-driven cybersecurity analysis 𝗧𝗲𝗰𝗵 𝗦𝘁𝗮𝗰𝗸 ↳ Generative AI / LLM • OpenAI, GPT-4, Llama 3, Mistral • LangChain, LlamaIndex • Hugging Face Transformers ↳ Machine Learning • Python, PyTorch, TensorFlow • Scikit-learn, Pandas ↳ Vector Search & RAG • Pinecone, Milvus, FAISS • Embeddings and semantic search ↳ Infrastructure • Docker, Kubernetes • AWS, GCP, Azure ↳ Computer Vision • OpenCV • YOLO • Vision Transformers 𝗦𝗲𝗹𝗲𝗰𝘁𝗲𝗱 𝗔𝗜 𝗨𝘀𝗲 𝗖𝗮𝘀𝗲𝘀 • 𝗘𝗻𝘁𝗲𝗿𝗽𝗿𝗶𝘀𝗲 𝗞𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 𝗔𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁 Secure RAG system enabling employees to search and interact with thousands of internal documents without data leakage. • 𝗙𝗶𝗻𝗧𝗲𝗰𝗵 𝗙𝗿𝗮𝘂𝗱 𝗗𝗲𝘁𝗲𝗰𝘁𝗶𝗼𝗻 𝗦𝘆𝘀𝘁𝗲𝗺 Real-time machine learning platform detecting fraudulent transactions across high-volume payment streams. • 𝗛𝗲𝗮𝗹𝘁𝗵𝗰𝗮𝗿𝗲 𝗗𝗶𝗮𝗴𝗻𝗼𝘀𝘁𝗶𝗰 𝗦𝘂𝗽𝗽𝗼𝗿𝘁 3D medical image processing system supporting diagnostic analysis with ~95% accuracy. • 𝗠𝘂𝗹𝘁𝗶-𝗔𝗴𝗲𝗻𝘁 𝗔𝗜 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄 AI agents coordinating information retrieval, analysis, and automated task execution within enterprise systems. 𝗪𝗵𝘆 𝗖𝗹𝗶𝗲𝗻𝘁𝘀 𝗪𝗼𝗿𝗸 𝗪𝗶𝘁𝗵 𝗠𝗲 • Security-first architecture (GDPR / HIPAA-ready) • Enterprise-grade engineering experience • Deep expertise in AI infrastructure, optimization, and system performance I focus on building AI systems that are reliable, scalable, and ready for real-world use. 𝘐𝘯𝘷𝘪𝘵𝘦 𝘮𝘦 𝘵𝘰 𝘺𝘰𝘶𝘳 𝘫𝘰𝘣 𝘧𝘰𝘳 𝘢 𝘱𝘳𝘦𝘭𝘪𝘮𝘪𝘯𝘢𝘳𝘺 𝘤𝘰𝘯𝘴𝘶𝘭𝘵𝘢𝘵𝘪𝘰𝘯 𝘵𝘰 𝘥𝘪𝘴𝘤𝘶𝘴𝘴 𝘺𝘰𝘶𝘳 𝘳𝘰𝘢𝘥𝘮𝘢𝘱 𝘢𝘯𝘥 𝘧𝘦𝘢𝘴𝘪𝘣𝘪𝘭𝘪𝘵𝘺.

𝐋𝐨𝐨𝐤𝐢𝐧𝐠 𝐭𝐨 𝐮𝐩𝐠𝐫𝐚𝐝𝐞 𝐲𝐨𝐮𝐫 𝐛𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐰𝐢𝐭𝐡 𝐀𝐫𝐭𝐢𝐟𝐢𝐜𝐢𝐚𝐥 𝐈𝐧𝐭𝐞𝐥𝐥𝐢𝐠𝐞𝐧𝐜𝐞? You are at the right place. I am Sajeel Hashmi, an AI Engineer with 5+ years of experience designing sophisticated neural architectures tailored to specific data challenges. My expertise lies in building systems that can interpret visual, linguistic, and sequential datasets, ensuring each model is backed by rigorous research and optimized for real-world impact. 𝐄𝐱𝐩𝐞𝐫𝐭𝐢𝐬𝐞 𝐂𝐨𝐦𝐩𝐮𝐭𝐞𝐫 𝐕𝐢𝐬𝐢𝐨𝐧: I create systems that interpret images, video, including object detection, segmentation, OCR pipelines, video analytics, and modern multimodal models combining vision and language for richer understanding. 𝐍𝐚𝐭𝐮𝐫𝐚𝐥 𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐏𝐫𝐨𝐜𝐞𝐬𝐬𝐢𝐧𝐠: I develop tools that read and analyze text like a human, classifying content, extracting insights, summarizing documents, and making large text collections searchable and structured. 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐯𝐞 𝐀𝐈 & 𝐋𝐋𝐌-𝐏𝐨𝐰𝐞𝐫𝐞𝐝 𝐀𝐩𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧𝐬: I build conversational assistants, retrieval-augmented systems (RAG), knowledge tools, and agent workflows powered by large language models to answer questions, automate tasks, and reason through complex queries. 𝐌𝐚𝐜𝐡𝐢𝐧𝐞 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠 𝐝𝐫𝐢𝐯𝐞𝐧 𝐩𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐨𝐧𝐬 𝐚𝐧𝐝 𝐢𝐧𝐬𝐢𝐠𝐡𝐭𝐬: I deliver predictive and analytical models that forecast outcomes, cluster patterns, and support decision-making, turning raw data into meaningful predictions. 𝐓𝐢𝐦𝐞 𝐒𝐞𝐫𝐢𝐞𝐬 𝐅𝐨𝐫𝐞𝐜𝐚𝐬𝐭𝐢𝐧𝐠: I work with temporal data to predict trends, detect anomalies, and optimize processes, helping teams plan better, reduce risk, and operate efficiently. 𝐓𝐞𝐜𝐡 𝐒𝐭𝐚𝐜𝐤 • Deep Learning: PyTorch, TensorFlow, Keras, Hugging Face Transformers, QLoRA, LoRA, ONNX, Quantization, Pruning. • Computer Vision: OpenCV, Ultralytics (YOLO), Segmentation, OCR (EasyOCR, KerasOCR), VLMs. • NLP & GenAI: Tokenizers, spaCy, NLTK, Vector Search (Faiss, Chroma, Pinecone), RAG pipelines, Agentic workflows. • Data & Analytics: NumPy, Pandas, SciPy, Statsmodels, SQL, XGBoost, LightGBM, ARIMA, Prophet. • Deployment & Backend: FastAPI, Django, Docker, GitHub Actions, REST APIs, Redis + Celery, Cloud GPU Inference. 𝐖𝐡𝐲 𝐂𝐥𝐢𝐞𝐧𝐭𝐬 𝐖𝐨𝐫𝐤 𝐖𝐢𝐭𝐡 𝐌𝐞 I help clients turn complex AI ideas into real-world impact. • Proven Results: High-performing AI systems that generate measurable value. • End-to-End Solutions: From data prep to deployment, all integrated smoothly. • Scalable & Production-Ready: Reliable systems with automated workflows and cloud deployment. • Technical Rigor: Leveraging the latest research in CV, NLP, and Generative AI. 𝐋𝐞𝐭’𝐬 𝐂𝐨𝐥𝐥𝐚𝐛𝐨𝐫𝐚𝐭𝐞 If you’re looking for an AI engineer to turn ideas into real-world solutions, let’s connect! I specialize in delivering impactful, production-ready systems. Reach out today to discuss your project.

Clients come to me at every stage. A fully scoped idea, a raw problem, or an existing system that needs to be modernized or have AI layered into it. I have worked across all of these and I know what each one demands. What I take care of on every engagement is the full picture. The architecture decisions that prevent expensive rewrites later, the AI integrations that actually hold up in production, the backend systems that scale under real load, and the product thinking that keeps the end user at the center of every decision. I work with solo founders validating their first idea, startup teams scaling their product, and enterprise teams modernizing legacy systems or building intelligent automation on top of existing infrastructure. On the technical side I cover: Frontend: React, Vue.js, Next.js, Nuxt Backend: Node.js, Express.js, NestJS, Python, FastAPI, Django, Flask, REST APIs, GraphQL AI and ML: OpenAI, Anthropic Claude, Google Gemini, RAG Pipelines, Vector Databases, Semantic Search, Computer Vision, NLP, Speech Recognition, Prompt Engineering Databases and Cloud: PostgreSQL, MongoDB, Firebase, Supabase, AWS, Azure, Google Cloud, Docker, Kubernetes Most of my work today sits at the intersection of AI and real business problems. Recruitment automation, healthcare intelligence, authentication systems, conversational AI, semantic search, and workflow automation are the kinds of problems I solve regularly. I am your single point of contact throughout. You will always know where things stand and why decisions are being made. When we are done everything is fully documented and fully yours. If you are building something serious and you need someone who thinks about your business first and writes code second, let us talk.

10 years at Microsoft | 5 US patents | Cambridge PhD in Computer Science I build production AI systems and tools for great performance, accuracy and reliability: LLM inference and runtimes, RAG pipelines, and agentic systems. Faster and correct code analysis and transformations within compiler/runtimes for verification and optimization purposes. Recent work: a local LLM runtime that saved 541 seconds through KV cache optimization, a RAG classification system at 95%+ accuracy, and an AI agent querying SQL databases with millions of records. Whatever you're building, I've likely engineered the layer underneath it. 𝗟𝗟𝗠 𝗜𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 & 𝗥𝘂𝗻𝘁𝗶𝗺𝗲 • Local deployment: llama.cpp, Ollama, vLLM, GGUF, TensorRT-LLM, MLX • Models: LLaMA, Mistral, Phi, Qwen, DeepSeek, Hugging Face Transformers • Optimization: KV cache, speculative decoding, continuous batching, tensor & pipeline parallelism • Fine-tuning: LoRA, QLoRA, PEFT, RLHF, DPO, distillation, quantization • GPU: CUDA, cuDNN, TensorRT, multi-GPU, distributed inference 𝗥𝗔𝗚 & 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 • Vector stores: FAISS, Pinecone, Milvus, ChromaDB, Qdrant • Search: hybrid search, dense retrieval, BM25, GraphRAG, knowledge graphs • Embeddings: OpenAI, Gemini, Mistral, open-source models • Delivered: real-time RAG classification system, 95%+ accuracy in production 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜 • Frameworks: LangChain, LangGraph, MCP • Capabilities: tool calling, function calling, memory systems, reflection, self-correction, planning • Delivered: AI agent over SQL databases with millions of records, 5-star review 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 The layer most AI engineers never touch, and the reason my systems hold up when others break. • Languages: Python, Rust, C++, C Compiler optimizations, static analysis, instrinsics, loop unrolling, verification • Runtime: CUDA, cuDNN, NCCL, LLVM, MLIR, JIT, AOT • Low-level: SIMD, AVX, SSE, OpenMP, OpenCL, lock-free programming, POSIX, epoll • Profiling, benchmarking, kernel optimization, distributed training 𝗪𝗵𝘆 𝗰𝗹𝗶𝗲𝗻𝘁𝘀 𝘄𝗼𝗿𝗸 𝘄𝗶𝘁𝗵 𝗺𝗲 ① PhD in compiler and static analysis: I know if the system is right, not just if it runs ② 10 years at Microsoft: I know what production reliability actually requires ③ Full-stack depth: from CUDA kernels to agent orchestration to RAG pipelines ④ Every project delivered, every client satisfied I work with funded startups, scale-ups, and engineering teams building serious AI infrastructure across any industry. 𝗧𝗲𝗹𝗹 𝗺𝗲 𝘄𝗵𝗮𝘁 𝘆𝗼𝘂'𝗿𝗲 𝗯𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗮𝗻𝗱 𝘄𝗵𝗲𝗿𝗲 𝗶𝘁'𝘀 𝗯𝗿𝗲𝗮𝗸𝗶𝗻𝗴. 𝘼𝙧𝙚𝙖𝙨 𝙄 𝙬𝙤𝙧𝙠 𝙖𝙘𝙧𝙤𝙨𝙨: LLM Inference & Serving: llama.cpp, Ollama, vLLM, GGUF, MLX, TensorRT-LLM, Hugging Face Transformers Model/Code Optimization: quantization, LoRA, QLoRA, PEFT, fine-tuning, distillation, prompt tuning, RLHF, DPO Inference Engineering: GPU inference, multi-GPU, tensor parallelism, pipeline parallelism, KV cache, speculative decoding, continuous batching Retrieval & RAG: hybrid search, vector search, GraphRAG, knowledge graphs, embedding models, FAISS, Milvus, Pinecone, ChromaDB, Qdrant Agentic AI: multi-agent systems, MCP, tool calling, function calling, memory systems, workflow engines, planning, reflection, self-correction Systems & Runtime: C++, C, Rust, Python, LLVM, Clang, MLIR, static analysis, memory management, JIT, AOT, thread scheduling, lock-free programming Performance Engineering: SIMD, AVX, SSE, OpenMP, OpenCL, CUDA, profiling, benchmarking GPU Computing: cuDNN, TensorRT, NCCL, kernel optimization, distributed training, distributed inference, compiler optimizations