AI Agent Engineer

Hi, we’re Vstorm!

We are a boutique AI Agent engineering consultancy specializing in process automation and transformations based on Agentic AI and RAG systems. Organizations around the world – from the USA, through Europe, to the Middle East – rely on our expertise to move from AI experimentation to real implementations that deliver measurable business results.

For our innovative approach to applying artificial intelligence in business, we have been recognized by EY, Deloitte and Forbes. We collaborate with global brands such as Intel, Mercedes, and leading self-publishing organizations in the UK.

Vstorm is the first-ever partner of PydanticAI, and the first consulting company to join the Agentic AI Foundation — giving our engineers direct exposure to the ecosystem shaping the future of Agentic AI.

Today, we’re expanding our A-players team and looking for an AI Agent Engineer who wants to work at the intersection of cutting-edge technology, real business problems, and long-term product thinking.

What you will do:

• focus on building LLM-based software (mostly for US-based companies),
• build projects from scratch OR maintain and scale existing projects,
• collaborate with business consultants (our team members) to help potential clients design a strategy,
• create documentation for projects,
• conduct code reviews to ensure best practices, optimize performance, and maintain high code quality,
• research and experiment with LLM-based technologies to unlock new capabilities and improve application performance,
• validate and evaluate the implemented technologies,
• contribute to building VstormPedia (our internal technical knowledge database).

Requirements:

• Bachelor’s degree in Computer Science, Machine Learning, or a related technical field, or equivalent practical experience.
• 2+ years of professional experience in software engineering/development, with a strong focus on building and deploying machine learning or AI-powered applications.
• Proven experience in developing LLM-based software, including hands-on experience with frameworks relevant to agent/workflow orchestration (e.g., PydanticAI, LangChain, LlamaIndex).
• Experience working with vector databases (e.g., Pinecone, Milvus, Qdrant).
• Experience in building LLM-based software using LangChain, LlamaIndex, FastAPI, etc.
• Demonstrable experience in designing, building, and optimizing RAG pipelines.
• Proven ability to create and manage validation/evaluation pipelines for LLMs.
• Understanding of Natural Language Processing (NLP) concepts and Large Language Model development.
• Proficiency with containerization (Docker) and at least one major cloud provider (AWS, GCP, or Azure).
• Proficiency with Git and software engineering best practices (clean code, CI/CD, code reviews).
• Proficiency in English at B2/C1 level (both written and spoken).
• Availability from 14:00 to 18:00 Polish time during working days (overlap with US time zones).

Nice to have:

• Direct experience with PydanticAI.
• Contributions to open-source AI or ML projects.
• Experience building and maintaining scalable REST APIs using frameworks like FastAPI or Flask.
• Experience with relational databases.

What we offer:

• B2B contract with competitive monthly compensation – hourly rate up to 140 PLN (rate defined individually, based on experience and impact).
• We’re fully remote by default, but at the same time, we value real human connection: we often work in hybrid mode and regularly meet to build a strong team… and have some fun :).
• Flexible working hours – we’re focused on trust, ownership, and outcomes.
• Long-term collaboration – we don’t hire for single projects, we build stable, expert-level teams.
• Up to 8000 PLN gross annual personal budget – fully yours to invest in learning, tools, conferences or anything that supports your growth and lifestyle.
• Daily collaboration with highly experienced AI engineers, including PhD-level specialists.
• Space and support to create and contribute to open-source projects, co-author research papers, technical articles, and thought leadership content, as well as experiment with your own ideas and transform them into real initiatives.
• Access to and influence over our internal knowledge base – Vstormpedia, continuously developed and enriched by the team – knowledge that stays, evolves, and compounds inside Vstorm.

At Vstorm, you join a team where expertise, curiosity, and ambition are taken seriously – and where engineers are trusted to think, create, and shape the future of Agentic AI.

Ready to apply?

Here’s what the process looks like:

1. Screening call – 20-30 min – our People & Operations Manager, Agnieszka will tell you more about the position and our projects, learn more about your background and experience so far, and check if we’re a good fit for each other.
2. Technical interview – approx. 1-1,5h – an in-depth interview with one of our Tech Leads to properly evaluate your theoretical and practical knowledge, your skills and experience. 
3. CEO interview – approx. 1h – a final meeting with Antoni, our CEO.
4. Decision – hopefully, we make you an offer and you accept it! 🙂

PS. We don’t ghost! Clear communication and relevant feedback has great value to us, so we’ll keep you informed during the whole process.

Got questions?
Feel free to contact recruitment@vstorm.co!

recruitment@vstorm.co