About
This role is focused on building production-grade Generative AI systems, especially Retrieval-Augmented Generation (RAG), internal knowledge platforms, and AI-driven automation. It is a hands-on engineering position, not a prompt-writing role, and supports the move of GenAI proofs of concept into reliable production solutions.
What you’ll do
Implement core RAG pipelines including ingestion, chunking, embedding, retrieval, and response generation Develop Python-based services and APIs that integrate Large Language Models (LLMs) Assist in building agent-based workflows with tool/function calling Work with vector databases and hybrid search mechanisms Participate in debugging hallucinations, retrieval failures, and quality issues Write clean, testable, and maintainable code Collaborate with senior engineers to move GenAI POCs into production
Who you are
2+ years of experience with Python programming and backend development Understanding of REST APIs and backend service development Basic understanding of LLMs, tokens, context windows, and hallucination Foundational knowledge of embeddings and vector search Familiarity with Git and standard software development practices
Perks
Remote work Full-time role Medical insurance Competitive pay and benefits Health insurance Language courses Relocation program Certification programs Mentorship and talent investment programs Internal mobility and internship opportunities Global client projects Inclusive multicultural environment Social events
MATCH FREE