LLM Platform Engineer

Start Date: ASAP / Within 1 Month / Flexible

Work Model: 100% remote 

Contract Type: B2B (160-180 PLN/h + VAT

We are seeking an LLM Platform Engineer to support the deployment, optimization, and operational management of large language models across GPU‑accelerated Kubernetes environments. In this role, you will work with modern Nvidia technologies and contribute to high‑performance inference pipelines used in real production scenarios. You will collaborate with platform, infrastructure, and DevOps teams to ensure reliable model delivery, efficient resource utilization, and scalable automation. 

Responsibilities

• Deploy, manage, and maintain AI/ML models with a focus on large language model (LLM) training, inference, and fine‑tuning.

• Configure and optimize LLM parameters to improve inference throughput, latency, and GPU utilization.

• Enhance inference workloads and fine‑tuning pipelines, including batching, scaling, and performance tuning.

• Work with Nvidia technologies such as Run:AI, Nvidia GPU Cloud, and Nvidia AI Enterprise within Kubernetes/OpenShift environments.

  
  

Expectations

• Experience deploying or operating ML/LLM workloads on Kubernetes or similar container platforms.

• Understanding of GPU‑accelerated inference, model optimization, and performance debugging.

• Hands‑on experience with CI/CD practices and automation, ideally using Azure DevOps or another modern toolchain.

• Familiarity with Nvidia AI tools (Run:AI, NGC, AI Enterprise) or equivalent ML infrastructure technologies.

What We Offer

• Medicover healthcare package

• Multisport card

• Access to an e-learning platform

• Group life insurance