AI Platform Engineer

As a Senior AI Platform Engineer - ML Infrastructure and RAG Systems, you will be working for our client, a leading multinational tech company focused on transforming AI-driven solutions across industries. You will contribute to developing and maintaining internal AI services, APIs, and retrieval systems that serve research, engineering, and operational needs. This role offers a unique chance to influence AI service delivery and support technological innovation at scale.

Location & work model

Wroclaw-based opportunity with an on-site work model.

Your main responsibilities:

• Develop and maintain internal AI services and APIs for production environments.
• Build and optimize RAG pipelines, including document ingestion, embeddings, retrieval, and relevance tuning.
• Manage vector database performance, scalability, and data freshness to ensure high retrieval quality.
• Design clear, well-documented APIs to support internal users and workflows.
• Integrate model serving endpoints into application-layer systems, ensuring low latency and high reliability.
• Define and monitor service objectives related to latency, reliability, and retrieval quality.
• Implement prompt management, versioning, evaluation, and testing frameworks for LLMs.
• Build resilient systems with fallback and degradation mechanisms to ensure continuous operation.
• Implement monitoring, tracing, logging, and quality metrics to oversee AI services' health and performance.
• Manage the lifecycle of AI services including deployment, rollout, updates, and deprecation.
• Participate in operational support and incident response to troubleshoot and resolve issues swiftly.

You're ideal for this role if you have:

• 4+ years of experience in software or platform engineering, with exposure to AI/ML or LLM applications.
• Strong Kubernetes skills and experience working with containerized environments.
• Good knowledge of AWS, networking fundamentals, IAM, and cloud infrastructure.
• Hands-on experience building and operating production RAG systems.
• Familiarity with vector databases and retrieval systems.
• Strong Python programming skills and experience developing production APIs and services.
• Solid understanding of LLM fundamentals, including prompting, token management, and output reliability.
• Excellent communication skills and the ability to work collaboratively across technical and non-technical teams.

It is a strong plus if you have:

• Experience with agentic AI systems and workflow orchestration.
• Knowledge of LLM evaluation frameworks and quality measurement techniques.
• Exposure to model serving platforms and inference optimization.
• Understanding of embedding model trade-offs and retrieval performance tuning.
• Data engineering experience or AI-related data pipelines.
• Relevant AWS or Kubernetes certifications.

Language Required for the role:

Fluent English, with excellent communication skills.