09/18/2026 updated
100 % available
Full Stack AI Engineer | LangChain, AutoGen, CrewAI | Multi-Agent Systems
Warszawa, Poland
Only remote
Cracow University of Technology - Bachelor of Computer ScienceAbout me
I’m a Full Stack AI Engineer passionate about building autonomous agents. With 10+ years of experience, Over the past few years, I’ve worked creating everything from research & data-gathering bots to trading systems, customer support agents, and IVR voice assistants.
LangChainJava (Programming Language)JavaScriptPHPApplication Programming Interfaces (APIs)Artificial IntelligenceDevOpsDjangoPython (Programming Language)PostgreSQLNode.jsAzure Machine LearningNext.jsTypeScriptPyTorch
AI & Machine Learning
Expertise in Artificial Intelligence, OpenAI API, AI Agent Development, LangChain, AutoGen, CrewAI, RAG pipelines, LLM fine-tuning, Voice AI, GenAI, and ChatGPT API Integration. Building and deploying production-ready intelligent systems including multi-agent architectures with memory, planning, and tool integration.
Backend & Server Development
Proficiency in Python, Java, Spring Boot, Django, Node.js, PHP, FastAPI, Express.js, RESTful APIs, and GraphQL. Design and implementation of high-throughput event processing systems, scalable SaaS platforms, and reliable webhook delivery pipelines.
Frontend Technologies
Strong command of React, Vue.js, Next.js, Angular, TypeScript, JavaScript, and Tailwind CSS. Development of custom components, internal dashboards, and patient intake portals with a focus on resilient, cross-browser compatible frontend code.
Databases & Storage
Hands-on experience with PostgreSQL, MySQL, MongoDB, Redis, Firebase, Supabase, DynamoDB, and Pinecone for vector storage to support semantic document retrieval.
LLM Integration & Abstraction
Architecture of abstraction layers enabling seamless switching between multiple LLM providers such as OpenAI, Anthropic, and open-source models running on GPU instances, based on cost and latency requirements.
NLP & Transformer Models
Building and fine-tuning transformer-based models for sentiment classification using PyTorch and the Hugging Face ecosystem, iterating quickly through different model architectures for financial services use cases.
Model Evaluation & Monitoring
Design of evaluation frameworks that track model drift over time, including automated retraining triggers that activate when performance drops below defined thresholds.
Python ML Libraries & AI Platform Development
Utilization of Python ML Libraries for building and productizing internal NLP research into sellable API products, including RAG pipelines pulling SEC filings and news articles into context windows.
Expertise in Artificial Intelligence, OpenAI API, AI Agent Development, LangChain, AutoGen, CrewAI, RAG pipelines, LLM fine-tuning, Voice AI, GenAI, and ChatGPT API Integration. Building and deploying production-ready intelligent systems including multi-agent architectures with memory, planning, and tool integration.
Backend & Server Development
Proficiency in Python, Java, Spring Boot, Django, Node.js, PHP, FastAPI, Express.js, RESTful APIs, and GraphQL. Design and implementation of high-throughput event processing systems, scalable SaaS platforms, and reliable webhook delivery pipelines.
Frontend Technologies
Strong command of React, Vue.js, Next.js, Angular, TypeScript, JavaScript, and Tailwind CSS. Development of custom components, internal dashboards, and patient intake portals with a focus on resilient, cross-browser compatible frontend code.
Databases & Storage
Hands-on experience with PostgreSQL, MySQL, MongoDB, Redis, Firebase, Supabase, DynamoDB, and Pinecone for vector storage to support semantic document retrieval.
LLM Integration & Abstraction
Architecture of abstraction layers enabling seamless switching between multiple LLM providers such as OpenAI, Anthropic, and open-source models running on GPU instances, based on cost and latency requirements.
NLP & Transformer Models
Building and fine-tuning transformer-based models for sentiment classification using PyTorch and the Hugging Face ecosystem, iterating quickly through different model architectures for financial services use cases.
Model Evaluation & Monitoring
Design of evaluation frameworks that track model drift over time, including automated retraining triggers that activate when performance drops below defined thresholds.
Python ML Libraries & AI Platform Development
Utilization of Python ML Libraries for building and productizing internal NLP research into sellable API products, including RAG pipelines pulling SEC filings and news articles into context windows.
Experience
Professional experience10+ years
Freelancer since2016
Languages
EnglishFluentPolishNative speaker
Project history
Technical lead for a greenfield project building an AI-powered knowledge management platform for mid-sized manufacturing companies. Architected the system using Next.js for the frontend and FastAPI on the backend, with PostgreSQL and Pinecone for vector storage. Integrated multiple LLM providers (OpenAI, Anthropic, open-source GPU models) via a custom abstraction layer. Implemented a feedback loop to capture user corrections and fine-tune embeddings, improving relevance metrics over time.
Productized internal NLP research into a sellable API product for financial services clients. Built and fine-tuned transformer-based models for sentiment classification on earnings call transcripts using PyTorch and Hugging Face. Built a RAG pipeline pulling relevant SEC filings and news articles into the context window. Designed an evaluation framework tracking model drift with automated retraining triggers.
Worked on a multi-tenant SaaS platform helping logistics companies manage fleet operations in real time. Led backend design using Spring Boot, focusing on high-throughput event processing and reliable webhook delivery. Rebuilt the notification pipeline, cutting message latency by nearly 40% and significantly reducing failed deliveries. Collaborated with frontend and DevOps teams to define clean API contracts and improve system observability.
Certificates
AI Engineer Professional Specialization
Coursera2025
Generative AI with Large Language Models (LLMs)
Programmer Hopes2023
Full Stack Developer
Coursera2020