CodeTiburon is looking for a Senior Backend Engineer (LLM & AI Infrastructure) to join our team.
About the project:
We are a deep-tech company building state-of-the-art LLM-based assistants augmented with knowledge graphs. The platform focuses on combining large language models with structured knowledge systems to create more accurate, reliable, and scalable AI assistants.
The project involves building robust backend infrastructure that powers AI applications, enabling scalable model inference, retrieval systems, and knowledge graph integrations within a multi-tenant SaaS environment.
Responsibilities: * Architect and implement scalable backend services and multi-tenant SaaS systems * Design and operate high-throughput data pipelines (batch and streaming) * Build APIs and services integrating LLM inference, retrieval systems, and knowledge graphs * Productionize research-grade AI systems into reliable distributed systems
Requirements (Must Have): * 7+ years of backend engineering experience * Strong experience with data pipelines and SaaS architectures * Strong proficiency in Python * Deep understanding of distributed systems and cloud-native environments
Nice to Have: * Go and/or Scala experience * Hands-on experience with LLM systems (RAG, model serving, evaluation) * Experience with knowledge graphs, vector databases, or hybrid retrieval architectures
Ideal for engineers who enjoy building production-grade systems around cutting-edge AI research.
If this sounds like you and you have most of the skills and qualifications above, please send your CV.
We sincerely thank all applicants for applying; if we like what we see and feel you are a match for our position, we will be in touch.