🚀 Stop managing manual workflows. Scale with Autonomous Operations. I architect Intelligent Business Engines that transform fragmented manual labor into high-performance, AI-driven ecosystems. As a Business Systems Architect with over 3,789+ billed hours and a Top-Rated Plus track record, I bridge the gap between complex Python engineering and agile Low-Code environments to build "Digital Workers" that think, decide, and execute. Agentic AI Full‑Stack. ### 🛠️ 𝐓𝐞𝐜𝐡𝐧𝐢𝐜𝐚𝐥 𝐒𝐭𝐚𝐜𝐤 : ✔️ Automation: n8n, Make, Zapier, Pipedream, Skyvia ✔️ AI Frameworks: OpenAI, Claude, LangChain, CrewAI, Scikit-Learn, Pandas, NumPy ✔️ Data & Scripting: Python (Django/Flask, Pandas), Apps Script, SQL ✔️ CRMs & Business Tools: Zoho One, HubSpot, Salesforce, Airtable, QuickBooks, GHL(Go HighLevel) ### 🤖 𝐂𝐨𝐫𝐞 𝐒𝐩𝐞𝐜𝐢𝐚𝐥𝐢𝐳𝐚𝐭𝐢𝐨𝐧𝐬 : ✔️ Autonomous AI Agents: I build custom, goal-driven agents using Claude 3.5, GPT-4o, and LangChain for automated decision-making and data extraction. ✔️ Multi-Step Orchestration: I design advanced enterprise workflows engineered in n8n, Make, and Zapier. ✔️ Intelligent Chatbots & RAG: I develop context-aware, Retrieval-Augmented Generation (RAG) systems for internal knowledge retrieval and automated lead qualification. ✔️ Machine Learning & Predictive Analytics: I train and deploy custom ML models for predictive scoring, intelligent categorization, and advanced pattern recognition. ✔️ Custom Scripting & Backend : I apply advanced Python, Google Apps Script, and SQL to turn standard tech stacks into powerful, unified business applications. ### 🏆 𝐖𝐡𝐲 𝐒𝐭𝐫𝐚𝐭𝐞𝐠𝐢𝐜 𝐏𝐚𝐫𝐭𝐧𝐞𝐫𝐬 𝐂𝐡𝐨𝐨𝐬𝐞 𝐌𝐞 : ✅ 𝐀𝐫𝐜𝐡𝐢𝐭𝐞𝐜𝐭𝐮𝐫𝐞 𝐅𝐢𝐫𝐬𝐭: I audit your business logic first, ensuring my systems solve core strategic needs rather than just connecting APIs. ✅ 𝐄𝐧𝐭𝐞𝐫𝐩𝐫𝐢𝐬𝐞 𝐑𝐞𝐬𝐢𝐥𝐢𝐞𝐧𝐜𝐞: I build advanced error handling, custom logging, and fail-safe mechanisms into every deployment for maximum uptime. ✅ 𝟕𝟎–𝟗𝟎% 𝐎𝐯𝐞𝐫𝐡𝐞𝐚𝐝 𝐑𝐞𝐝𝐮𝐜𝐭𝐢𝐨𝐧: I engineer solutions to eliminate manual friction so your team can focus strictly on growth. ### 📅 𝐍𝐞𝐱𝐭 𝐒𝐭𝐞𝐩𝐬 : 𝗥𝗲𝗮𝗱𝘆 𝘁𝗼 𝘁𝗿𝗮𝗻𝘀𝗶𝘁𝗶𝗼𝗻 𝗳𝗿𝗼𝗺 𝗺𝗮𝗻𝘂𝗮𝗹 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀 𝘁𝗼 𝗮 𝗯𝘂𝘀𝗶𝗻𝗲𝘀𝘀 𝗼𝗻 𝗮𝘂𝘁𝗼𝗽𝗶𝗹𝗼𝘁? Click "𝐌𝐞𝐬𝐬𝐚𝐠𝐞" or "𝐈𝐧𝐯𝐢𝐭𝐞" to discuss your system audit or custom AI deployment.

Hello, I am a Full Stack Developer with over 7 years of experience in product development, specializing in building scalable applications, intelligent automations, and data-driven solutions using Django, FastAPI, GoLang, React, and Generative AI. Technical Specializations Generative AI & Agentic AI: Agentic AI workflow design, Claude Code, Claude Cowork, AI-assisted development (Cursor) Workflow Automation: n8n, Make, Zapier Full-Stack Web Development: Django, Flask, FastAPI, GoLang (Gin), React, Postgres, MongoDB Data Analytics & Big Data: Python, Pandas, NumPy, PySpark, Apache Spark, Kafka, Hive Charts & Visualizations: D3.js, Highcharts.js, Chart.js, Google Charts, Interactive React Dashboards Cloud & DevOps: GCP, AWS, Heroku, Docker, Kubernetes, CI/CD pipelines Architecture: Microservice Architecture, Product Architecture Design, Scalable Solutions Data Extraction: Advanced Web Scraping & third-party API integration Services I Offer Generative AI & Agentic Workflows: Developing autonomous AI agents, implementing LLM-backed solutions, and leveraging cutting-edge tools like Claude Code, Claude Cowork, and Cursor for accelerated, high-quality development. Low-Code/No-Code Automation: Designing seamless, automated workflows and data pipelines using n8n, Make, and Zapier to connect disparate systems and optimize business processes. Custom Web Development: Building robust, secure, and high-performance full-stack web applications using Django, FastAPI, React, and GoLang (Gin). Data Analytics & Visualization: Processing complex datasets with Pandas and PySpark, and turning insights into interactive, user-friendly React dashboards. API Development & Integration: Creating custom RESTful APIs and integrating complex third-party APIs (Google, Facebook, Instagram, government portals, etc.). Web Scraping & Data Extraction: Extracting and structuring data from dynamic, complex, and heavily secured web sources. Application Deployment & DevOps: Containerizing and deploying scalable applications on AWS/GCP using Docker and Kubernetes. Big Data Processing: Utilizing Apache Spark, Kafka, and Hive for large-scale, real-time data processing and analytics. About Me I have a proven track record of working successfully with both agile startups and large multinational companies. I thrive on challenging projects, continuous learning, and pushing the boundaries of what's possible with modern AI and automation technology. I am deeply committed to honesty, transparency, and discipline. I adapt to shifting project requirements with ease and consistently deliver high-quality work ahead of schedule, ensuring complete client satisfaction.

🔝 TOP-RATED Freelancer | 8+ Years of Expertise | Data Analyst & Web Scraping Specialist 🌍 Trusted by clients across USA, UK, Ireland, Canada, Australia, Germany, New Zealand, Singapore, Netherlands, UAE, and more. 🙋🏻‍♂️ Hi, I'm Maunik Vekariya, a seasoned data professional with 8+ years of hands-on experience in Web Scraping, Data Extraction, Automation, and Data Visualization using Power BI and Tableau. I specialize in turning raw, complex data into meaningful business insights and high-volume, scalable scraping solutions. ✅ What I Offer: ✔ Web Scraping & Crawling (Websites & Mobile Apps) ✔ Business Lead Generation ✔ Data Analytics & Visualization ✔Automation Scripts & Bots ✔ Custom Dashboards & Reporting ✔ Bulk Data Extraction (1M+ records/day) ✔ LinkedIn Automation (Auto connect & message) 🛠 Technical Stack: ✔ Languages/Tools: Python (BeautifulSoup, Scrapy, Selenium, Requests, Lxml, Regex, Pandas, Numpy), .NET (C#, VB, HtmlAgilityPack), R, VBA/Excel ✔ Dashboards & BI: Power BI, Tableau, DAX, Power Query ✔ Infrastructure: AWS, OVH, BigRock, GoDaddy ✔ Databases: MySQL, SQL Server, PostgreSQL ✔ Advanced: Proxy rotation, Captcha bypass, Bot detection evasion, Traffic tracing 📊 Key Projects: ✔ Data analysis of London Fire Brigade, Job Portals, Pharmacies, Ecommerce, Stock Markets, and Hospital Systems ✔ Scraped platforms like Amazon, Walmart, Zillow, Expedia, LinkedIn, Glassdoor, YellowPages, and more ✔ Built tools for store locators, tender scraping, and LinkedIn automation 🎯 Why Work With Me? 🏆 Upwork Top-Rated 🔄 Unlimited Revisions — I deliver exactly what you need 🚀 Rapid Turnaround & Scalable Results 🤝 Professional Communication & Client Satisfaction Focused 📬 Let’s connect and bring your data project to life with precision, speed, and excellence.

AI & Software Engineer | Specializing in Generative AI, Machine Learning I am experienced in building intelligent systems and optimizing cloud infrastructure with extensive hands-on experience in AI, data engineering, and cloud technologies. With a proven track record of delivering scalable, efficient, and tailored solutions, I’m here to help bring your tech vision to life. ————————— You are here because ————————— - You are a small to mid-sized startup or business pushing the boundaries of technology. - You need custom AI or cloud solutions that go beyond pre-built options and offer a competitive edge. - You need expert guidance in automating workflows, deploying AI models, and optimizing cloud infrastructure to scale. - You’re looking for a tech partner who can handle everything from data pipelines to machine learning models, and deliver results. ——————————— Here’s why I’m the right fit: ——————————— I specialize in building and deploying complex AI solutions that automate tasks, optimize processes, and scale with your business. My experience spans multiple industries, and I’ve delivered everything from predictive data pipelines to advanced machine learning models. I work with technologies like Python, AWS, GCP, and Ansible to provide end-to-end solutions. ——————————— I help my clients: ——————————— - Develop and deploy intelligent systems (e.g., LLM assistants, predictive models, and image enhancement). - Optimize cloud infrastructure (AWS/GCP) for maximum performance. - Automate workflows using Ansible and monitor critical operations with Grafana. - Build robust data pipelines using PySpark, Airflow, and BigQuery. ——————————— More about me: ——————————— With a strong foundation in AI, cloud computing, and software development, delivering custom solutions that drive business outcomes. My projects range from automating customer support with AI assistants to designing scalable data pipelines for real-time data processing. I use tools like AWS SageMaker, Docker, and Kubernetes to build production-ready solutions. Whether you need an AI-powered application or cloud infrastructure optimization, I’m here to guide you through the entire process, from planning to execution. For more details on my projects and how I can assist you, check out my portfolio below. Let’s collaborate and bring your tech vision to life!

⭐️ Top Rated - Top 10% of Talent on Upwork 🕒 7+ Years of Experience in Data Science & Business Intelligence ✅ Successfully Delivered 133+ Projects ✅ Supported Over $2M+ in Data-Driven Business Decisions ✅ Excelling in delivering Fortune 500-scale Projects Hi! I'm a Senior Data Scientist, Data Analyst, and Power BI Developer with 7+ years of experience turning messy data into clean insights, reliable Machine Learning models, and deployment-ready AI solutions for startups, SMEs, and enterprise teams. I work as a hands-on data & AI partner from exploratory data analysis and statistical modelling to production ML pipelines, Power BI dashboards, and Deep Learning workflows. Send me a dataset, notebook, GitHub repo, or paper and I'll turn it into a working, documented solution. ━━━━━━━━━━━━━━━━━━━━━━━━━━━ 🏆 Accomplishments ━━━━━━━━━━━━━━━━━━━━━━━━━━━ ⭐ Top Rated — Top 10% of Data Science & Analytics talent on Upwork ⭐ 133+ projects across Data Science, ML, Deep Learning, Data Analysis & Power BI ⭐ $2M+ in data-driven business decisions supported across finance, healthcare & SaaS ⭐ Fortune 500-scale BI pipelines, ML solutions & reporting automation delivered ━━━━━━━━━━━━━━━━━━━━━━━━━━━ 🎯 Core Services ━━━━━━━━━━━━━━━━━━━━━━━━━━━ 📊 Data Science, Data Analysis & Statistics EDA, hypothesis testing, regression analysis, time series analysis, predictive analysis, statistical analysis, A/B testing, cohort analysis, clinical data preprocessing, medical data analysis, survey analysis, financial analysis, and business reporting — Python, R, SQL, Excel. 📈 Power BI, BI & Data Visualization Power BI dashboards, DAX optimization, Power Query, KPI systems, executive reporting, self-service analytics, ETL/ELT pipelines, data warehousing, star schema, data modeling, performance tuning, marketing analytics, financial reporting, and forecasting — Tableau, Looker Studio, Excel. 🧠 Machine Learning & Model Training Regression, classification, multi-class classification, clustering, anomaly detection, churn prediction, forecasting, recommendation systems, trading signals, risk scoring, sports prediction — feature engineering, model evaluation, explainable AI, and reproducible Python notebooks. 🤖 AI Development, Deep Learning & LLMs LLM fine-tuning, RAG chatbots, AI agents, NLP pipelines, text classification, semantic search, embeddings, TTS, text-to-image, document processing, AI simulations, multimodal AI, Deep Learning pipelines, and web app model integration — OpenAI, Hugging Face, LangChain, PyTorch, TensorFlow. 👁 Computer Vision & Image AI Object detection, object tracking, image classification, image segmentation, 2D/3D pose estimation, OCR, medical image analysis, satellite data, and COLMAP workflows — OpenCV, YOLO, PyTorch. 📡 Data Engineering, Scraping & Automation Web scraping, ETL pipelines, API integration, data cleaning, sensor data, SQL databases, and automation workflows — preparing datasets for ML, AI, and Data Science projects. 🔁 GitHub & Hugging Face Repo Reproduction Research paper implementation, repo debugging, notebook fixing, model fine-tuning, dependency resolution, and turning experimental code into production-ready solutions. ━━━━━━━━━━━━━━━━━━━━━━━━━━━ 🛠 Tech Stack ━━━━━━━━━━━━━━━━━━━━━━━━━━━ Data Science & Analytics: Python, R / RStudio, SQL, Excel, Statistics, Pandas, NumPy, Scikit-learn, SciPy, Statsmodels BI & Visualization: Power BI, DAX, Power Query, Tableau, Looker Studio, Excel Dashboards, Matplotlib, Seaborn, Plotly Machine Learning & AI: TensorFlow, PyTorch, Keras, Hugging Face, LangChain, OpenAI API, YOLO, OpenCV, spaCy, NLTK, XGBoost, LightGBM, RAG, LLM fine-tuning Data Engineering & Databases SQL Server, PostgreSQL, MySQL, ETL Development, Data Warehousing, Data Modeling, Azure Data Services, API Integration, BeautifulSoup, Scrapy ━━━━━━━━━━━━━━━━━━━━━━━━━━━ ✅ Hire Me For ━━━━━━━━━━━━━━━━━━━━━━━━━━━ ✅ Power BI dashboards, DAX, automated reporting & executive BI ✅ ML models: regression, classification, forecasting, anomaly detection ✅ LLM fine-tuning, RAG chatbots, NLP & AI app integration ✅ Computer vision: detection, segmentation, 2D/3D pose estimation ✅ EDA, statistical analysis, A/B testing & research visualisation ✅ ETL pipelines, web scraping & data engineering ✅ Research paper & GitHub/Hugging Face repo reproduction ✅ Medical AI, clinical data, sensor data & trading signal models You can send me a dataset, Excel/CSV file, database, API, sensor data, sports data, medical data, notebook, paper, GitHub repo, Hugging Face model, or incomplete codebase, and I will turn it into a clean, working, documented solution. Let's connect and make your data work for you.

Are you looking for a Data Scientist who can transform your data into actionable insights and build AI solutions that solve real business problems? With 5+ years of professional experience, I specialize in developing end-to-end Data Science and Machine Learning solutions from data collection and preprocessing to model development, evaluation, and deployment. I have worked with startups, research teams, and businesses across multiple industries, helping them leverage data to make smarter decisions and automate complex workflows. My background combines strong analytical thinking with hands-on industry experience, allowing me to deliver solutions that are not only accurate but also scalable and production-ready. My Expertise, ✅ Data Science & Machine Learning ⦁ Predictive Modeling ⦁ Classification & Regression ⦁ Clustering & Segmentation ⦁ Feature Engineering ⦁ Model Selection & Optimization ⦁ Statistical Analysis ⦁ Time Series Forecasting ⦁ Model Evaluation & Deployment ✅ Artificial Intelligence ⦁ Machine Learning ⦁ Deep Learning ⦁ Computer Vision ⦁ Natural Language Processing (NLP) ⦁ Large Language Model (LLM) Applications ⦁ Retrieval-Augmented Generation (RAG) ⦁ AI Automation ✅ Python & Data Analytics ⦁ Python (Pandas, NumPy, Scikit-learn) ⦁ TensorFlow & PyTorch ⦁ SQL ⦁ Data Cleaning & Preprocessing ⦁ Exploratory Data Analysis (EDA) ⦁ Data Visualization (Matplotlib, Plotly) ✅ Data Engineering & Automation ⦁ ETL Pipelines ⦁ Apache Airflow ⦁ Airbyte ⦁ API Integration ⦁ AWS ⦁ Workflow Automation 💼 Recent Projects ✔ Developed machine learning models for agricultural spectroscopy to predict moisture content and chemical properties from NIR spectral data. ✔ Built an AI-powered WhatsApp customer support system using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). ✔ Designed and automated scalable ETL pipelines using Apache Airflow and Airbyte for ingesting and processing data from multiple APIs. ✔ Developed deep learning models for medical image analysis, including diabetic retinopathy detection. ✅ Why Clients Choose Me * 5+ years of industry experience in Data Science and Artificial Intelligence. * Strong expertise in Machine Learning, Deep Learning, NLP, and Python. * Experience building production-ready AI solutions, not just research prototypes. * Clean, maintainable code with a focus on performance and scalability. * Clear communication, timely delivery, and long-term client relationships. Whether you need to build a predictive model, develop an AI-powered application, automate data workflows, or extract valuable insights from your data, I'm committed to delivering solutions that create measurable business value. Let's discuss your project and build something impactful together!

Top Rates Plus - awarded to the top 3% of Upwork freelancers! Experienced Senior Statistical Programmer with over 8 years of expertise in clinical trials and pharmaceutical research across therapeutic areas including oncology, cardiology, dermatology, gastroenterology, neurology, hematology, Real World Evidence (RWE), peptides and vaccines studies. Strong leadership capabilities in coordinating programming activities and timelines across multiple studies in phases I-IV. Dedicated to maintaining data integrity and supporting efficient clinical trial operations. Proficient in the development of statistical computing environments and serving as a clinical trials subject matter expert (SME) for software development companies supporting clinical research solutions. For a detailed overview of my hands-on responsibilities and real-world contributions, please refer to the Employment section, which outlines how this expertise has been applied across clinical trial development and pharmaceutical research projects. I hold Bachelor of Data Science degree from the American University of Armenia. My educational background, combined with hands-on experience, has equipped me with a robust skill set and a deep understanding of statistical methodologies and programming languages relevant to the clinical trials domain. My technical skills include proficiency in: SAS Programming (Advanced Level Certified, see in the 'Certifications' section): • Advanced SAS/BASE, SAS, SQL, SAS/MACRO, SAS/GRAPH, SAS/STAT, SAS/PROC, ODS output • SAS Viya (cloud version), Integration with R and Python, SAS Visual Analytics • Arrays, Hash Objects, Advanced Indexing, Memory Management • Handling large and complex datasets with efficient I/O and parallel processing techniques • Advanced macro writing, debugging and dynamic code generation, nested and recursive macros • Git/version control tools R Programming: • Clinical packages - pharmaverse, admiral, sdtmoak, tfrmt, gtsummary, PKNCA • Data manipulation and transformation - tidyverse, dplyr, tidyr, purrr, stringr, lubridate, tibble (implicit), readr (implicit) • Data visualization - ggplot2, plotly, gtsummary (dual-purpose), gt, flextable, patchwork, cowplot • High-quality analytical reports - rmarkdown, knitr, quarto • Interactive dashboards and applications using R Shiny Python Programming: • Python core (data types, control flow, functions, modules), NumPy, pandas, SciPy. • Clinical data processing with pandas (joins, reshaping, group summaries, derivations comparable to SDTM/ADaM workflows). • Integration with SAS and R (reading/writing SAS datasets via pyreadstat, interoperability for QC and validation). • Data visualization and reporting (matplotlib, seaborn, Excel/CSV outputs, automated report generation). • Advanced data handling (vectorization, memory optimization, chunked processing, handling large datasets). • Statistical analysis in Python (descriptive statistics, hypothesis testing, regression, survival analysis using lifelines). • Validation and quality control frameworks (independent QC of SAS outputs, data consistency checks, audit-friendly logs). • Unit testing and code quality (pytest, structured logging, reproducible environments). • Metadata and XML processing (Define-XML handling, CDISC metadata validation using xml/lxml). Power BI & Business Intelligence: • Design and development of interactive Power BI dashboards for exploratory and operational analytics • Data modeling using Power BI semantic models, relationships, and star-schema concepts • Data transformation and preparation using Power Query (M language) • KPI development, filters, drill-downs, and slicers for executive-ready reporting • Integration with multiple data sources (CSV, Excel, SQL databases, APIs) • Performance optimization for large datasets (model size, relationships, DAX efficiency) • Secure sharing and collaboration using Power BI Service Project Management: Working with Jira, Scrum, GitHub Microsoft Office tools: Microsoft Word, Excel, PowerPoint, Access, Outlook Driven by a passion for continuous learning and a collaborative spirit, I am known for my easy-going demeanor and my ability to thrive in team environments within the clinical trials field. I approach each project with dedication and attention to detail, consistently delivering results that exceed expectations and contribute to the advancement of clinical research.

Greetings, I’m an experienced Data Scientist You hire me when your data is messy, scattered, or under-used. I help you turn raw data into clear insights and automated systems that support real business decisions. You don’t just get analysis. You get clarity, structure, and action. 🔹 What I Help You Do Build interactive dashboards that track performance clearly Develop predictive models for forecasting, churn, and classification Clean, transform, and structure messy datasets Automate data pipelines (ETL) using Python & SQL Extract data from APIs, websites, and databases reliably 🔹 Tools I Use Daily Python (Pandas, NumPy, Scikit-learn, TensorFlow) SQL (PostgreSQL, MySQL) Power BI / Tableau / Excel Machine Learning & Deep Learning Web Scraping & Data Extraction 🔹 What You’ll Get Working With Me Clean, well-documented code Clear explanations (no jargon overload) On-time delivery Solutions built for scalability, not just demos Honest communication and progress updates I treat your project like a business problem — not just a task. 🔹 Typical Projects I Handle Sales & operations dashboards Customer churn or demand prediction Data cleaning and feature engineering SQL reporting and optimization Automated reporting workflows If your data should be working harder for you, I can help. Send a message. Let’s turn your data into decisions. Best regards, Annette

👋 Hi! I’m a Data Analyst / Data Engineer skilled in SQL, Python, Excel, and data visualization — ready to help you turn raw data into clean, reliable, and actionable insights. I can also help you build new systems or improve existing workflows to create more efficient and scalable data processes. Whether you need help cleaning messy datasets, building analysis-ready data models, or creating intuitive dashboards, I’ve got you covered. Recent Achievements: ✅ Improved a client's existing data processing workflow, reducing manual effort and increasing efficiency by 60%. ✅ Recommended and implemented a new data visualization solution that made charts and reports more user-friendly, leading to improved user feedback and increased membership growth. Here’s what I can do for you: 🛠️ Extract and automate data pipelines using Python (including APIs and web sources) 📊 Organize, structure, and maintain data in Excel or Google Sheets 🧼 Clean, transform, and model data using SQL and Power Query 📈 Build clear, interactive dashboards in Power BI, Looker Studio, or Tableau 📬 Communicate clearly and consistently to keep your project on track I’m genuinely passionate about making data useful and reliable, and I bring a strong mix of technical skills and business understanding to every project. Let’s make your data work smarter for you 💡

Top 3% Freelancer who built enterprise multi-tenant RAG systems with custom LLM deployments, reduced LLM workflow costs by 70%, and delivered a 2M product data quality pipeline for a Fortune 500 biotech company, reducing manual efforts by 85%. Architected and deployed production systems across finance, biotech, energy, telecommunications, and healthcare. 5+ years taking end-to-end ownership on all projects, from greenfield architecture to secure & scalable production deployment, leading engineers and maintaining systems long-term. I specialize in production-ready AI solutions with measurable ROI. From 90% accuracy voice classification to billion-scale data engineering. Core Expertise: • AI Agents / Agentic Workflows (LangGraph, Tool Calling, Function Calling, Agent Memory Patterns, Agent Patterns, Multi-Agent Orchestration, Building MCP, Plugins, Skills, Hooks, Deterministic Enforcement, ReAct Pattern, AI Assistants, Research, Planning, Writing) • LLM Systems (Claude API, OpenAI API Integration, vLLM, LoRA/QLoRA Fine-Tuning, PEFT, RLHF, DPO, LLaMA, Mistral, Prompt Engineering, Deterministic Workflows, LLM Evaluation, Cost Optimization, Deploying Chatbots, Deploying LLMs, Claude Code, Codex) • RAG (Hybrid Retrieval, Vector Databases, Evaluation Harness, Tiered Access, Custom Document Parsing, PDF/Clinical Data Extraction, Ragas, Multi-Tenancy) • NLP (Transformers, spaCy, Named Entity Recognition, Text Classification, Taxonomy Design, Rule-Based Extraction, Sentiment Analysis, Topic Modeling, Summarization, Information Extraction) • Generative AI (Structured Outputs, Pydantic Validation, Guardrails, Hallucination Prevention, AI Chatbot Development, AI Integration) • ETL & ML Pipelines • Time Series Applications at scale. - I personally prefer native APIs for building Agentic / LLM workflows. Domain Expertise: • Energy & Utilities (demand forecasting, carbon emissions, time series, pricing optimization) • Financial Services (compliance-ready RAG, churn prediction) • Life Sciences (biotech product classification, scientific NER, clinical data extraction, safety) • Telecommunications (voice classification, Whisper, ASR, diarization) Projects - Open source contributor (Langchain vLLM integration fix) - Enterprise RAG Engine with multi-tenancy, project-level isolation, custom vLLM deployments, agent live on the WhatsApp channel - customer support. - Finance-Specific RAG System with compliance features and RAG benchmarking - Enterprise Knowledge Base Chatbots Integrating (RAG daily sync on Notion, Slack, Website, Documents, evals, Live on Zendesk Customer Support Agent, Internal AI Agents on Slack(Deep Research, Q-A, Reporting), Blogpost creation with tone and fact checks.) - Production agentic workflows with state management, semantic processing, and monorepo CI/CD - SEO keyword clustering system processing 10k+ keywords under 10s using OpenAI embeddings + HDBSCAN - Enterprise Misspelling Detection Pipeline for 2M biotech products using FAISS similarity matching and 740k scientific corpus validation (Thermo Fisher) - Real-time Voice Classification System (90% accuracy, active learning pipeline) - Call Recommendation System with statistical engine for optimal calling times - Energy Market Forecast System for Budapest electricity prices - 500+ Class Text Classification with Fine-Tuned BERT - Extending a Lexicon using GloVe Word Embeddings - Databricks PySpark Data Pipeline for Aggregating Billion Scale Data - Time Series Analysis and Models on Energy Consumption Data from different locations in Belgium and Germany - API Integrations & Calculations on Electricity Business Objectives - Imbalanced Binary Classification on Anonymized Data (Oversampling + CatBoost & hGBM) - Data Processing Pipeline for 70m of Electricity Sensor Data for a Research Project Tech Stack: • Programming Languages: Python, SQL • Machine Learning & Deep Learning: TensorFlow, Keras, PyTorch, Scikit-Learn • NLP: LangChain, NLTK, Gensim, FAISS, Pinecone, pgvector • Time-Series: Prophet, TSMixer, ARIMA, SARIMAX, LSTM • MLOps & Data Engineering: Terraform, Linux, Apache Spark, Airflow, Docker, Flask, Streamlit, Gradio, MLflow, W&B, Optuna, CI/CD Pipelines, n8n workflows, Ragas • Cloud: Google (BigQuery, Cloud Functions, Cloud Run, Dataflow, Vertex AI, Firestore, Cloud Storage, Composer) • AWS (Lambda, SageMaker, S3, EC2, ECR, DynamoDB, Glue, CloudWatch) • Azure (Databricks-PySpark) • Database: PostgreSQL, Pinecone, Chroma • Data Manipulation & Statistics: Pandas, NumPy, OpenCV, Regex, SciPy, Statsmodels • Data Visualization: Matplotlib, Plotly • Web Scraping: BeautifulSoup, Requests • Building Custom NER Models & Linking, Question Answering, Text Similarity & Word Embeddings, Part-of-Speech Tagging & Dependency Parsing, Text Generation, Lexical Semantics & N-grams, Clustering • Logistic Regression, SVM, Decision Trees, Random Forest, Gradient Boosting Machines (XGBoost, LightGBM, hGBM), k-NN, CNN, RNN, K-Means, DBSCAN, HDBSCAN, OPTICS