AI / Full Stack Engineer (TypeScript/Node.js, React)
Webellian
This role combines full-stack TypeScript/Node.js development with applied AI — building production systems that integrate LLMs, RAG pipelines, and vector search. You will work on client projects in diverse industries, designing and deploying AI-powered features while owning the full stack from frontend to infrastructure. The position is consulting-oriented, meaning you may shift between projects and need to quickly adapt to different business contexts.
Brak jawnych widełek — wynagrodzenie do ustalenia podczas rekrutacji.
Brakuje: team size and structure, recruitment process (number of stages, technical test, etc.).
This role combines full-stack TypeScript/Node.js development with applied AI — building production systems that integrate LLMs, RAG pipelines, and vector search. You will work on client projects in diverse industries, designing and deploying AI-powered features while owning the full stack from frontend to infrastructure. The position is consulting-oriented, meaning you may shift between projects and need to quickly adapt to different business contexts.
- ✓Opportunity to work with local GPU infrastructure and cutting-edge AI tooling
- ✓Autonomy and ownership over technical decisions
- ✓Projects described as 'no boring CRUD work' — focus on AI and challenging problems
- ✓Mentoring opportunities within a collaborative team
- !No details on hybrid work schedule (number of days in office per week)
- !Team size not specified (only 'small, collaborative team')
- !Consulting context may involve switching between client projects and technologies
- !No mention of on-call or after-hours support
- !Recruitment process not described
- ?Brak jawnych widełek — wynagrodzenie do ustalenia podczas rekrutacji
- •Designing and developing full-stack applications with AI capabilities using TypeScript/Node.js, Nest.js, and React
- •Deploying, configuring, and optimizing LLMs (both cloud APIs and self-hosted on GPU infrastructure)
- •Building and maintaining RAG pipelines, vector stores, and knowledge retrieval systems
- •Integrating AI systems with external services and APIs (e.g., OpenAI, custom models)
- •Evaluating model performance, choosing appropriate models, and making trade-off decisions
- •Writing clean, maintainable code with tests and documentation
- •Proposing technical improvements and architectural decisions
- •Mentoring less experienced team members and reviewing code
Oferta dla doświadczonych specjalistów (Senior).
A strong mid-level (4-5 years) full-stack developer with TypeScript/Node.js/React who has started working with LLMs and RAG, perhaps via side projects or recent work, and is eager to deepen their AI expertise. They should meet the soft skills and communication requirements.
People without at least 4-5 years of full-stack experience or without any practical exposure to LLMs and RAG. Also not for those who prefer pure backend or pure AI research without full-stack responsibilities.
- ?How many people are in the immediate team?
- ?What is the typical hybrid schedule — how many days per week in the Warsaw office?
- ?Can you describe a typical client project duration and team composition?
- ?What specific GPU infrastructure is available for self-hosted LLMs?
- ?Is there a budget for cloud APIs like OpenAI, or do we primarily use self-hosted models?
- ?How does knowledge sharing work across projects?
- ?What is the onboarding process like for new client projects?
- −Team size and structure
- −Recruitment process (number of stages, technical test, etc.)
- −On-call or support expectations
- −Project rotation frequency
- −Specifics of GPU infrastructure (model, capacity)
Small, collaborative team with autonomy and mentoring culture, focused on challenging AI-driven projects.