Eventum AI
Lead AI / RAG Engineer: Self-Hosted Knowledge Platform
1 мес. назад
65–90 USD / часСтрана неизвестнаLeadRemote
pythondockerterraformkubernetesci/cdvector searchllmembeddings
Eventum AI builds production-grade LLM, RAG, agent, and document-intelligence systems. The role involves leading the architecture and implementation of a production RAG knowledge platform with responsibilities including ingestion, retrieval, generation, deployment, and evaluation.
About the company
- Eventum AI builds production-grade LLM, RAG, agent, and document-intelligence systems.
Responsibilities
- Lead architecture and implementation of a production RAG knowledge platform
- Build ingestion for Google Workspace, PDFs, scans, tables, and images
- Implement ACL-aware retrieval, hybrid search, reranking, and citation-backed generation
- Deploy and benchmark open-weight models with vLLM or similar
- Build evaluation, observability, CI/CD, and production handoff
Requirements
- 6+ years of software/ML engineering experience
- Strong production LLM/RAG and Python/backend experience
- Experience with embeddings, vector search, reranking, and document pipelines
- Experience serving open-weight LLMs with vLLM, SGLang, Triton, TGI, or similar
- Strong cloud/infrastructure skills: Docker, Terraform/Kubernetes, or CI/CD
- Experience with LLM evaluation and production reliability