Senior AI Platform Engineer

We are looking for a hands-on AI Platform Engineer to design, build, and maintain the Enterprise Agent Development Platform, a production-grade, cloud-native ecosystem that enables engineering teams to define, orchestrate, deploy, and observe AI agents at scale. The role includes standardizing agent development across the organization, implementing advanced agentic evaluation frameworks using AWS AgentCore, and building robust LLM-as-a-judge and CI/CD deployment gates to reduce development from months to days while enforcing strict security and quality standards. Strong Python skills and deep expertise in LLM evaluation are required, along with experience in cloud infrastructure.

Responsibilities

• Develop and launch scalable conversational AI systems that operate across multiple channels, including chat, voice, email, and APIs.
• Architect microservices and asynchronous systems for AI applications, ensuring high availability and performance.
• Use Python to implement orchestration and decision logic—the control layer that manages tools, workflows, and system interactions.
• Design evaluation frameworks for autonomous agents, tracking multi-step workflows, tool-calling accuracy, and session performance; integrate automated gates into CI/CD pipelines.
• Establish automated evaluation protocols utilizing LLM-as-a-judge patterns.
• Optimize AI models through fine-tuning and LoRA integration, making data-driven decisions between fine-tuning and RAG approaches.
• Work with data specialists to design pipelines for collecting, cleaning, and structuring information for AI agents.
• Design CI/CD pipelines, container standards, and cloud strategies for infrastructure migrations, cost optimization, and high availability.

Requirements

• Strong background in Python for integrating AI models, automation, and orchestration logic.
• 1–2 years of hands-on experience with Generative AI and large language models (LLMs).
• Practical machine learning engineering experience: data preparation, cloud vector databases, and model training/optimization.
• Expertise in agentic evaluation, including hands-on design of evaluation frameworks for complex multi-agent systems and evaluation of reasoning traces, tool selection, and agentic workflows.
• Proven experience building automated testing and evaluation gates within CI/CD pipelines for AI models.
• Strong backend and frontend architecture experience.
• Experience with AWS, GCP, or Azure, including container orchestration and CI/CD pipelines.
• Experience with agentic frameworks such as LangChain and LangGraph, and with multi-agent system design.
• Experience with TensorFlow, PyTorch, or Scikit-learn is a plus.

We offer

• Hybrid-by-design work mode and the opportunity to work remotely within Poland.
• Opportunity to work abroad for up to 60 days annually.
• Business-driven relocation opportunities.
• Career development programs.
• Thought leadership, mentoring, soft-skills, and well-being programs.
• Certifications in Anthropic, Gemini, GCP, Azure, and AWS.
• English classes.
• Stable pay.
• Participation in the Employee Stock Purchase Plan with a 15% discount.
• Benefits package, including health insurance, multisport, and shopping vouchers.
• Referral bonuses up to $2,000.
• Offices with entertainment and relaxation zones, table tennis and football, free snacks, coffee, and more.
• Corporate, social, and well-being events.

Benefits listed above are available to employees only. Contractors are welcome; terms of B2B cooperation agreements are agreed individually. Only selected candidates will be contacted.