RAG & LLM Architect — On-Prem AI Pipelines (Warsaw)

Diverse CG Sp. z o.o. Sp.k.; Warszawa; On-site; PLN 212,044 - 339,270; Full time

Job summary

Diverse CG Sp. z o.o. Sp.k. in Warsaw is seeking a skilled professional to architect and implement Retrieval Augmented Generation (RAG) pipelines tailored for enterprise applications. The ideal candidate will join a dynamic team and spearhead projects involving cutting-edge AI technologies and open-source large language models.

The role requires at least 3 years in ML/NLP, with a focus on deploying LLM-based solutions in on-premises or hybrid settings. A strong background in Python and experience with vector databases are essential. This position offers challenges in a vibrant work environment.

Qualifications

• At least 3 years of professional experience in ML/NLP roles, including 2+ years working with RAG systems.
• Proven experience deploying and operating LLM-based solutions in on-prem or hybrid environments.
• Hands-on experience with vLLM, LiteLLM, and open-source LLMs such as LLAMA 3.2.

Responsibilities

• Architect, implement, and optimize end-to-end Retrieval Augmented Generation (RAG) pipelines.
• Design and integrate retrieval mechanisms with generative models.
• Implement and customize inference servers for scalable LLM serving.

Skills

ML/NLP experience

Python

Problem-solving

Communication

Knowledge of vector databases

Linux systems

Education

Bachelor's, Master's, or PhD in Computer Science

Tools

PyTorch

Hugging Face Transformers

LangChain

Neo4j

Docker

Kubernetes

Job description

Diverse CG Sp. z o.o. Sp.k. in Warsaw is seeking a skilled professional to architect and implement Retrieval Augmented Generation (RAG) pipelines tailored for enterprise applications. The ideal candidate will join a dynamic team and spearhead projects involving cutting-edge AI technologies and open-source large language models.

The role requires at least 3 years in ML/NLP, with a focus on deploying LLM-based solutions in on-premises or hybrid settings. A strong background in Python and experience with vector databases are essential. This position offers challenges in a vibrant work environment.