Python AI/LLM Engineer

We build custom AI & LLM-based software. We help startups, scaleups, and tech companies to drive ROI by hyper-personalization, hyper-automation, and enhanced decision-making processes through AI and LLM-based software. Our mission is to help companies ethically implement AI, enabling people to focus on what truly matters.

We work with companies from the US, UK, and Canada from startups to companies from fortune 500. Our clients are featured in the Financial Times, Forbes, TechCrunch, Business Insider, etc.

In the Vstorm community you can:

• Enjoy a long-term, remote & hybrid job in a flextime plan
• Work on long-term international projects, where you could expand your skills
• Workation has never been easier, as we care about performance, not location
• Use our annual budget of up to 8000PLN gross to spend on what you love
• Monthly compensation is negotiable depending on your seniority level

We seek an experienced Python AI/LLM Engineer to join our mission. This is more than just a statement – it’s our daily practice and a core part of our DNA. We’re seeking an A-player who thrives on continuous learning, personal growth, and building AI Agentic solutions that impact businesses.

The project centers on developing an Agentic AI platform as a cornerstone of the AI transformation for a leading UK-based mid-size e-commerce company. Since we’re in the early stages, we’re building a team of exceptional talent to create custom AI Agents across multiple domains (this is pure engineering—no GPTs or off-the-shelf solutions). These agents will operate across various processes and business areas, providing diverse and intellectually stimulating work.

You’ll collaborate directly with the client’s team and our AI Tech Lead in sprint-based iterations. Our mission is to drive the AI Agents transformation, addressing immediate pain points while aligning with long-term strategic goals. This is an extended engagement focused on automating complex but routine processes throughout the e-commerce operation.

What will you do?

• Design & Implement production-grade AI Agents using PydanticAI.
• Develop Retrieval-Augmented Generation (RAG) pipelines and end-to-end AI workflows.
• Build RESTful and WebSocket APIs to expose AI functionalities.
• Prepare & Automate validation datasets, evaluation suites, and continuous testing for LLMs.
• Containerize services (Docker) and deploy on cloud platforms (AWS, GCP, or Azure).
• Optimize performance and ensure reliability, security, and observability in production
• Collaborate with business consultants (our team members) to help potential clients design a strategy 
• Creating documentation for projects 
• Conduct code reviews to ensure best practices, optimize performance, and maintain high code quality
• Contributing to building VstormPedia (our internal technical knowledge database) on a weekly basis 

Ideally, if you have:

• Bachelor’s degree in Computer Science, Machine Learning, or a related technical field.
• 2+ years of professional experience in software engineering/development using Python, 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).
• Demonstrable experience in designing, building, and optimizing RAG pipelines.
• Proven ability to create and manage validation/evaluation pipelines for LLMs.
• 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)

Got questions?
Feel free to contact Vstorm!

Vstorm Team