Strong Junior Applied AI Engineer (LLM/RAG)
Summary
Build and improve production AI systems using LLMs and RAG pipelines, integrating them with backend services and evaluating performance.
We are looking for an Applied AI Engineer to help our team design, develop, and improve production AI systems powered by LLMs.
Responsibilities
Develop and improve LLM and RAG pipelines.
Work with structured outputs, tool calling, and agentic workflows.
Integrate AI components with backend systems and external services.
Evaluate model performance and reduce errors.
Research and apply new AI approaches.
Use Claude Code, Codex, and other AI development tools.
Requirements
1+ year of commercial software development experience.
Strong knowledge of at least one programming language: Python, JavaScript/TypeScript, Java/Kotlin, C#, or another backend language.
Practical experience with LLM APIs or AI-powered features.
Understanding of RAG, embeddings, vector search, and prompt engineering.
Experience with APIs, databases, and Git.
Strong technical thinking, independence, and a desire to grow in Applied AI.
Python experience is a plus, but we are open to candidates with other strong technical backgrounds.
Nice to Have
Experience building LLM or RAG solutions.
Understanding of ML fundamentals, datasets, and AI system evaluation.
Experience with vector databases, FastAPI, Langfuse, LangChain, or LlamaIndex.
Experience with Docker, queues/workers, or event-driven systems.
Personal AI projects or open-source contributions.
We do not expect candidates to know everything listed above. Practical thinking, a strong technical foundation, and the ability to learn quickly are more important to us.
What We Offer
Fully remote work.
Work on real production AI systems.
The opportunity to influence architecture and technical decisions.
Practical experience with LLMs, RAG, AI evaluation, and agentic systems.
Minimal bureaucracy and direct communication with the team.
Opportunities to grow professionally together with the product.