AI Platform Engineer

Qube Research & Technologies; Wrocław; On-site; PLN 180,000 - 280,000; Full time

Job summary

Qube Research & Technologies seeks an experienced AI Platform Engineer in Wroclaw to build and operate internal AI services and APIs supporting researchers and engineers.

You will implement SOTA RAG pipelines, manage vector stores, ensure reliability, latency goals, and provide scalable solutions across the firm. The role emphasizes collaboration with Platform Engineering and data science teams in a fast-paced environment.

Qualifications

• 4+ years of software/platform engineering with AI/LLM exposure.
• Strong Kubernetes experience and containerised environments.
• Knowledge of AWS, networking fundamentals, IAM and cloud infra.
• Hands-on experience building/operating production RAG systems.
• Experience with vector databases and retrieval systems.
• Strong Python skills and building production APIs/services.
• Understanding of LLM fundamentals: prompting, context, tokens.
• Strong communication and cross-team collaboration.

Responsibilities

• Develop and maintain internal AI services and APIs.
• Build/improve RAG pipelines: ingestion, embeddings, retrieval, relevance.
• Manage vector database performance, scalability, freshness.
• Design clear, well-documented internal APIs.
• Support agentic workflows and dependent services.
• Integrate model serving endpoints into apps and services.
• Define/monitor latency, reliability, retrieval quality objectives.
• Implement prompt management, versioning, evaluation, testing.
• Build resilient systems with fallback/degradation mechanisms.
• Implement monitoring, tracing, logging, quality metrics.
• Manage deployment, rollout, versioning, deprecation lifecycle.
• Participate in operational support and incident response.

Skills

4+ years software/platform engineering

Kubernetes

AWS

LLM/AI exposure

Vector databases

Python

APIs & services

Communication

Tools

Kubernetes

AWS

Vector databases

Model serving platforms

Retrieval systems

Job description

Qube Research & Technologies (QRT) is a global quantitative and systematic investment manager, operating in all liquid asset classes across the world. We are a technology and data-driven group implementing a scientific approach to investing. Combining data, research, technology, and trading expertise has shaped QRT’s collaborative mindset, which enables us to solve the most complex challenges. QRT’s culture of innovation continuously drives our ambition to deliver high-quality returns for our investors.

You will build and operate QRT’s internal AI application platform, enabling researchers, developers, and data scientists to leverage LLM-powered tools effectively and reliably. Your focus will be on production AI services, including RAG systems, agentic workflows, retrieval infrastructure, and the APIs that make these capabilities available across the firm. You will work closely with Platform Engineering and AI users to deliver scalable, high-quality solutions.You will own AI services used across the firm and help shape how AI capabilities are delivered to researchers and engineers.

Your future role within QRT:

AI Platform Development

• Develop and maintain internal AI services and APIs
• Build and improve RAG pipelines, including document ingestion, embeddings, retrieval, and relevance optimisation
• Manage vector database performance, scalability, and data freshness
• Design clear, well-documented APIs for internal users
• Support agentic workflows and the services they depend on

Platform Reliability & Quality

• Integrate model serving endpoints into application-layer services
• Define and monitor service objectives around latency, reliability, and retrieval quality
• Implement prompt management, versioning, evaluation, and testing frameworks
• Build resilient systems with fallback and degradation mechanisms

Operations & Observability

• Implement monitoring, tracing, logging, and quality metrics across AI services
• Manage service lifecycle activities, including deployment, rollout, versioning, and deprecation
• Participate in operational support and incident response

Your present skillset:

• 4+ years of experience in software or platform engineering, with exposure to AI/ML or LLM-based applications
• Strong Kubernetes experience and familiarity with containerised environments
• Good knowledge of AWS, networking fundamentals, IAM, and cloud infrastructure
• Hands-on experience building and operating production RAG systems
• Experience with vector databases and retrieval systems
• Strong Python skills and experience building production APIs and services
• Understanding of LLM fundamentals, including prompting, context management, token constraints, and output reliability
• Strong communication skills and the ability to collaborate across technical and non-technical teams

Nice to Have

• Experience with agentic AI systems and workflow orchestration
• Familiarity with LLM evaluation frameworks and quality measurement
• Exposure to model serving platforms and inference optimisation
• Understanding of embedding model trade-offs and retrieval performance
• Experience with data engineering or AI-related data pipelines
• AWS or Kubernetes certifications

QRT is an equal opportunity employer. We welcome diversity as essential to our success. QRT empowers employees to work openly and respectfully to achieve collective success. In addition to professional achievement, we are offering initiatives and programs to enable employees achieve a healthy work-life balance.