AI Engineer (RAG & On Prem LLMs) RAG, LLM, Python, PyTorch, LangChain, Neo4j, Docker, Kubernete[...]

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

Job location: Warsaw

Responsibilities:

• Architect, implement, and optimize end-to-end Retrieval Augmented Generation (RAG) pipelines for enterprise use cases in on-premises environments
• Design and integrate retrieval mechanisms (e.g. vector databases such as Neo4j) with generative models (e.g. LLAMA 3.2, Mistral)
• Fine-tune and optimize retrieval and generation components to achieve high accuracy and low latency
• Implement and customize inference servers using vLLM and LiteLLM for efficient and scalable LLM serving
• Integrate open-source large language models with proprietary data sources and enterprise APIs
• Design GPU-optimized, scalable on-prem infrastructure for model training and inference, ensuring security and data governance compliance
• Collaborate with DevOps teams to containerize workflows using Docker and Kubernetes and automate MLOps pipelines
• Apply performance optimization techniques such as quantization, pruning, and dynamic batching
• Monitor system performance, troubleshoot bottlenecks, and ensure high availability
• Work closely with data engineers and business stakeholders to translate business requirements into technical AI solutions in telco environments

Requirements:

• 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, DeepSeek, or Mistral
• Strong Python skills and experience with frameworks such as PyTorch, Hugging Face Transformers, and LangChain
• Experience with vector databases (e.g. Neo4j)
• Familiarity with Linux‑based systems and Red Hat OpenShift
• Strong problem‑solving and analytical skills
• Ability to clearly communicate complex AI concepts to non‑technical stakeholders
• Bachelor's, Master's, or PhD degree in Computer Science, Artificial Intelligence, or a related field