Hire the Best Python Consultants
in Poland

👋 Hi, I'm Jakub. I build AI automation systems and AI agents that run real business operations end to end, so your team stops doing repetitive work by hand. I don't just wire two apps together with a Zap. I build production systems: teams of AI agents that make decisions and hand off to each other, automations that self-heal when something changes, and dashboards that show you exactly what's happening. My systems run on real cloud infrastructure and keep running when I'm not watching. 💼 What I Build → AI Agents & Multi-Agent Systems Reusable "teams" of AI agents where each has one job, clear permissions, and a clean handoff, with an independent agent that checks the work. Not one giant prompt trying to do everything. → AI Chatbots & Support Assistants Bots that answer from your own docs and knowledge base (RAG), qualify visitors, hand off cleanly when stuck, and plug into your website, WhatsApp, or CRM. → Workflow & Cloud Automation Your tools connected into one reliable flow using n8n, Make, and custom Python on serverless cloud infrastructure. Leads, orders, invoices, and data move automatically. → CRM, Dashboards & Reporting HubSpot, Salesforce, Airtable, Pipedrive wired into one system, plus live dashboards showing pipeline health, job status, and costs in real time. → Done-For-You AI Systems Full pipelines from first contact to paid. I built an AI "website factory" where a team of agents handles intake, design, coding, quality review, and deployment, and the only manual step is the phone call. It has produced live client websites on real domains, with payment collection and invoicing built in. 🏅 Selected Work → Built and run a fleet of production AI automations for an enterprise warehouse-software company with 6 business units, automating large parts of their sales and marketing: AI agents for research and outreach, website chatbots (RAG) across all 6 brands, a meeting-intelligence pipeline (recordings to summaries to CRM), lead qualification, and observability dashboards, all consolidated onto serverless cloud infrastructure. → Designed reusable multi-agent "organizations" with per-agent tool permissions and contract-first design, so builds stay reliable and verifiable instead of drifting. → Deep Claude / Anthropic ecosystem work: custom Claude Code skills, connected tool integrations (MCP), and headless scheduled AI agents that run automatically every day without me touching them. ⚙️ How I Work Three layers: clear documentation so you know what the system does, AI orchestration that makes the routing and decisions, and reliable code that runs the same way every time. Systems that get stronger over time instead of breaking when something changes. 👨‍💻 Tech Stack Python, Claude (Anthropic) & OpenAI APIs, AI agents (Agent SDK, MCP), n8n, Make, Modal, Supabase, Airtable, HubSpot, Salesforce, Pinecone, Playwright, Cloudflare, custom APIs & webhooks Let's talk about what you want to automate.

Hey! My name's Yana - founder of FrameGen Studio 💫 I create UGC-style and AI-avatar ads for Instagram, Tiktok, YouTube, Meta. Fast 24-48h video ads that drive more sales and leads. 🎬 I specialize in AI-generated UGC-style video ads for DTC and e-commerce brands, working at a flat rate: - Building consistent AI avatar/character systems for brands, locked reference sets across multiple angles so the same "presenter" holds up scene to scene and video to video, no drift. - Producing full campaigns from concept and hook development through generation and post (CapCut edit, ElevenLabs voice, motion/lip-sync workflows). - Working directly with Meta Pixel and Conversions API setups, and collaborating with clients' existing automation (n8n) rather than working in isolation. 📌 Some recent results: 212% CTR increase (Ravioli kit, Meta) 2.8x ROAS at scale (CookingGiftSet Co., Father's Day campaign) 4.1x ROAS and 89% lift in thumbstop rate (SugarLips, TikTok) 38% drop in cost-per-lead (Amerix clinic) 3.1x CTR (LAWSHARKS) 🤖 Beyond video, I build custom automation with Claude Code when a client needs something more than creative. Recent builds: - A SaaS application powering a personalized outreach system, generating actionable reports on monitored target accounts to fuel icebreaker-driven cold outreach. - An intelligence system delivering weekly actionable reports for B2B founders on how they can use AI right now. 🖥️ My stack: Higgsfield, Seedance 2.0, Kling, Runway Gen-4, ElevenLabs (voice), CapCut, Nano-Banana 2, plus Meta Ad Library research to build creative around what's already proven to work in a given niche before I generate a single frame.

Anthropic Certified • Full-Stack AI Implementation & Operations Typical engagements: - Audit your current AI workflow and identify high-value automation points - Build AI agents for repeatable research, writing, coding, analysis, or operations - Connect Claude, APIs, databases, documents, and internal tools - Create clear documentation so the system can be used after the engagement ends

🌟 Ready to Get Started? Unlock the potential of No-Code and Low-Code tools with my expert guidance. Whether you are a startup looking to build an MVP or a business aiming to streamline operations, I have you covered. Don't let coding challenges slow you down. Reach out to me today, and together, we'll make your app ideas come to life. 🛠️ My Expertise With extensive experience in No-Code and Low-Code tools, I specialize in crafting a wide range of applications. These range from internal tools that streamline business processes to robust MVPs that can attract potential investors for your startup. My key skills include: - WeWeb - Xano - Supabase - Airtable - Fastgen - PostgreSQL - n8n 💬 Client-Centric Approach I take pride in my client-centric approach, placing your success at the forefront of my service. I am committed to: 🤝 Collaborative Efforts: I closely collaborate with you to understand your unique goals and requirements, ensuring that the final product surpasses your expectations. 📈 Scalability: I design solutions with scalability in mind, ensuring that your app can grow seamlessly alongside your business. 📣 Ongoing Support: My services extend beyond project completion. I am here to provide continuous support and maintenance as required.

I'm a Solutions Architect and independent consultant specializing in Supabase. I help startups and engineering teams design, review, and scale production-ready applications built on Supabase. My work focuses on Supabase Architecture, Security Audits, and Performance Optimization. I help validate Row Level Security (RLS), tenant isolation, authorization, database design, scalability, and production readiness to reduce technical risk before launch. My expertise includes: * Supabase Consulting * Supabase Architecture Audits * Supabase Security & Tenant Isolation Audits * Supabase Performance Audits I also advise on modern data platforms and data engineering when organizations need a solid foundation for analytics, AI, and business intelligence.

I have Expert-Vetted Talent (EVT) badge - it's Upwork's top 1% freelancers — pre-screened by Upwork Talent Managers and experts in their field. Out of ~30 million programmers worldwide, only a few thousand know Algorithms & Data Structures better than I do, which is proven by programming competitions. Please, contact me if you need that skill level (top 0.01%). I can do algorithmic/performance work in C/C++, Python, SQL, Java, MQL4, MQL5, C#, Assembly, JavaScript, Julia, Rust, and probably other languages - learning them rapidly. I also work with AI, mostly in NLP and NLU: large language models including OpenAI GPT-3, Bloom, BloomZ, GPT-J 6B, LLaMA, Alpaca, etc.; HuggingFace Transformers, Accelerate; Petals, Deepspeed, zfp/zfpy; CUDA, CPU, and MPS (AArch 64 M2 MacOS Metal GPU) backends. I have some work experience with Apple Neural Engine (ANE). In AI, I also worked with XGBoost for predictions (including trading), LibSVM, TensorFlow, PyTorch, Scikit-learn, etc. I have the hardware in my home office for training and inference with large language models and other AI. English: C1 (Grammarly plugin says I use more unique words than 95% of other users, native speakers included). Polish: B1 (86%). Russian, Belarusian: Native. - With unique skills in Algorithms & Data Structures, I improve programs asymptotically (often 100 or more times on large input data). - 29 years of programming (started Basic and assembler on ZX Spectrum), 24 years of C/C++, 16 years of commercial work experience + 3 years of research projects. - Contributed to widely used Open Source projects: LLVM/Clang (my contribution is XRay profiler on ARM32 and AArch64 systems), Katana Graph (multiple small contributions mostly driven by the proprietary part where I do GPU/CUDA), CBMC "C Bounds Model Checking" (I contributed parallelized output of DIMACS formatted Boolean Satisfiability formula), oatpp (C++ web framework, I contributed bug-fixes), OWL (OptiX Wrapper Library, I contributed build fixes for Ubuntu), Galois (research project for distributed computations on graphs, I contributed GPU improvements) - Actively participated in bug reporting and reproduction (for NVIDIA CUDA, Cadical&kissat boolean satisfiability solver, JBOSS, MariaDB, Tensorflow, Linux, etc) - Led several open-source projects of my own: ProbQA (a video game recommendation system based on a high-performance Bayesian inference engine with CUDA, SIMD, and multi-threading); InSoAr (automatic reconstruction of software architecture from source code ), a multi-threaded Boolean Satisfiability solver, etc. Working for hire, implemented: - efficient multi-threading, scaling real-world workloads almost linearly with the number of CPU cores (128x for AMD Ryzen Threadripper 3990X) - SIMD vectorization (SSE/AVX), up to 8x improvement in computing thread or even copying (see my "Faster alternatives to memcpy" answer on Stackoverflow, URL upon request). - cache-aware algorithms: up to 50x improvement on some workloads - up to 20 trillion operations/second in CUDA (thousands of times faster than CPU) - up to the theoretical limit (6.8 Gigarays/second on RTX 2080 laptop GPU) in ray-tracing with OWL and OptiX - AVX512 and RTM (Restricted Transactional Memory) based acceleration, 16x improvement for float numbers -up to 20x improvements to cryptocurrency miners on CPU using AVX512 and cache-friendly algorithms - crypto-miners for Ethereum, Bittensor, Qubic 15K reputation on Stackoverflow: (1915854/serge-rogatch) Topcoder SRM score: 1480 - among top 5K programmers in the world - top 0.02% (rSerge) I developed all kinds of networking applications, from Linux Kernel modules up to Web applications. The majority of work was, of course, done at TCP/IP level with socket calls like send/recv/select. Programming languages: C++, C++11/14/17/20, C, Python, x86/x64/ARM/AArch64 assembly, SQL, C# .NET, JavaScript, HTML, CSS, Java, MQL4, MQL5, XML, Cypher, Rust. Libraries/Frameworks: PyTorch, Tensorflow, HuggingFace Transformers/Accelerate/Safetensors, Hivemind/Petals, OpenAI, tiktoken, Django, Flask, STL, LibSVM, XGBoost, libcurl, Selenium, PyTorch, Transformers. Technologies: OpenMP, CUDA, SIMD (AVX&SSE, RTM), Linux Kernel Modules, OptiX/OWL, RTX, raytracing. Theory/Principles/Know-how/Methodologies: Algorithms & Data Structures, Performance Optimization, Artificial Intelligence, Multithreading, Vectorization, OOP, Low-latency, High-frequency, Blockchain. Open source code: Clang, LLVM, LLVM's compiler-rt library, Linux Kernel, a few of my own repositories, contributions to AI and Algorithm open-source projects such as Petals and CBMC. Tools/APIs/Architectures/Platforms: PostgreSQL, MSSQL, MySQL, Neo4j, MATLAB, CMake, GIT, MT4, MetaTrader 5, Conda, PyCharm. Virtual Machines / Containers: Docker, VMWare, VirtualBox, QEmu, Hyper-V. OSes: Windows, Linux, Android, macOS