AI Automation Engineer – Build & Optimize LLM Agents

About the role

We are looking for an AI Automation Engineer to build AI agents that automate repetitive manual tasks and to deploy, optimize and run self‑hosted large language models (LLMs). You will turn multi‑hour manual processes into fast, cost‑effective automated solutions.

Key responsibilities

• Design and implement agents that automate document processing, code refactoring, deployment checks and data extraction for internal teams.
• Deploy, run and optimize self‑hosted LLM instances, improving inference speed and reducing infrastructure costs.
• Integrate LLM‑powered agents with existing systems, databases and production pipelines, and monitor their performance over time.

Required profile

• 3‑5 years of software engineering experience.
• Hands‑on experience deploying and running self‑hosted LLMs (not just API calls).
• Proven track record of building AI‑driven tools that are used in production.
• Strong proficiency in Python and basic Linux/infrastructure knowledge.
• Experience optimizing LLM inference speed and performance.

Required skills

• Python programming.
• Linux system administration.
• Git version control.
• Docker and basic DevOps.
• Self‑hosted LLM deployment and inference.
• Model optimization techniques such as quantization, batching or caching.
• GPU infrastructure and model serving.
• Agent frameworks (e.g., LangChain, AutoGPT, OpenClaw).

What we offer

• Direct impact by saving hours of manual work through automation.
• Opportunity to work with cutting‑edge LLM technology and GPU hardware.
• Fast feedback loop with visible results of your agents.
• Growth paths toward tech‑lead or specialist roles.
• Collaboration with a global team and direct interaction with founders.