Shape the future of AI-driven applications by leading the architecture and implementation of intelligent systems that solve real-world challenges. In this role, you'll take ownership of building and refining AI solutions from concept to production, ensuring they are scalable, reliable, and aligned with user needs.
What You’ll Do
- Design and deploy full-stack AI systems, covering data pipelines, model inference, and structured output delivery
- Develop and optimize Retrieval-Augmented Generation (RAG) architectures and autonomous agent workflows using tools like LangChain, LangGraph, and ADK
- Deploy and manage models on cloud platforms (AWS/GCP/Azure) using Docker and Kubernetes, with a focus on performance and uptime
- Establish feedback mechanisms and monitoring to track model accuracy, detect hallucinations, and identify drift over time
- Collaborate with engineers and product teams to integrate AI capabilities into core products and define feature scope
- Fine-tune open models such as Llama and Mistral for domain-specific tasks, balancing efficiency, latency, and cost
What We’re Looking For
- 5+ years of software engineering experience with a focus on AI or machine learning systems
- Proficiency in Python or related languages such as Scala, Java, or JavaScript
- Familiarity with Transformer models, embedding techniques, and vector search algorithms
- Hands-on experience with LLM APIs including OpenAI, Anthropic, and Google Vertex AI
- Proven work with agent frameworks like LangChain and LangGraph
- Experience using vector databases and managing both SQL and NoSQL data stores
- Working knowledge of cloud infrastructure, especially AWS or GCP
- Understanding of AI patterns such as RAG, few-shot prompting, and fine-tuning strategies
- Solid foundation in software engineering practices: Git, testing, and CI/CD pipelines
Nice to Have
- Experience with Google Cloud Platform services like Vertex AI, Firestore, and Cloud Functions
- Knowledge of advanced prompt engineering methods including Chain-of-Thought, ReAct, and Tree of Thoughts
- Background in building autonomous agent systems that interact with external tools or APIs
How We Support You
- Work remotely with flexibility and a budget to create your ideal workspace
- Access localized healthcare coverage and a monthly wellness stipend
- Enjoy flexible time off—minimum of 3 weeks plus holidays—and a culture that values rest
- Grow your skills with a personal learning budget and opportunities for professional development
- Focus deeply with no internal meetings on Fridays
- Connect in person at annual company offsites
- Receive a competitive salary, profit-sharing, and a paid sabbatical after several years
Work Environment
This is a fully remote role with a preference for candidates based in Poland, including Kraków, Wrocław, and Gdańsk. We operate in a flexible, trust-based model that prioritizes impact over presence.
Our Culture
We believe in building with care—both in the products we create and how we work together. Our team is curious, technically serious, and committed to solving meaningful problems. We value ownership, craftsmanship, and collaboration with others who take pride in their work. Here, the way you build matters as much as the outcome.
