AI Solutions Engineer

Our requirements

• Proven software engineering background delivering production services and automation within operational environments.
• Hands on experience with observability and operational data (logs, metrics, traces, alerts) and using these insights to prioritise engineering driven improvements.
• Strong programming and scripting skills (Python preferred) with expertise in APIs, webhooks and event driven architecture.
• Demonstrated DevSecOps mindset, continuous integration and delivery practices delivering small, safe, frequent changes.
• Skilled at building production ready tooling with monitoring, audit trails and supportability built in.
• Experience navigating complex organisations, driving delivery across multiple teams and priorities.
• Practical Agile delivery knowledge (Scrum or Kanban) with excellent documentation and collaboration habits.
• Fluent English (oral and written).
• Experience implementing AI or GenAI solutions for operations, including retrieval augmented generation over KBs and runbooks, or incident and change risk assistants.
• Understanding of Responsible AI, e.g. human in the loop design, auditability, AI incident response.
• Demonstrated ability to publish engineering standards, reference implementations, and automation golden paths for organisation wide reuse.

Optional

• Exposure to cloud environments (Azure, GCP, or AWS) and container orchestration (Kubernetes, Docker).
• Familiarity with observability stacks (Geneos, Grafana, Prometheus, Loki, Splunk).
• Experience with Python ML frameworks or APIs (OpenAI, Hugging Face, LangChain) in enterprise contexts.
• Knowledge of ITIL process integration and governance in AI service delivery.

Your responsibilities

• Lead engineering delivery for AIOps and automation use cases, such as:
• incident summarisation, alert correlation and routing suggestions, root cause and change risk assistants, communications and PIR drafting tools, patch/vulnerability intelligence.
• Design and implement secure integrations across operational ecosystems — monitoring, ITSM, knowledge bases, configuration sources — ensuring least privilege, proper audit and resilient error handling.
• Define measurable success indicators (MTTR reduction, alert noise reduction, adoption metrics, control quality) and instrument solutions to capture demonstrable impact.
• Build reusable, approved AI patterns (“paved roads”) covering data redaction, grounding and citation, evaluation, monitoring and runbook standards.
• Drive production governance — operational readiness, support model definition, dashboarding, incident playbooks, and rollback mechanisms for AI driven capabilities.
• Provide technical leadership on automation engineering practices, standardisation and compliance with service management controls.
• Participate in (or lead) production incident and problem management cycles to reduce recurrent failures.
• Communicate clearly with senior stakeholders, translating engineering delivery into measurable business and operational outcome.
• Note: Detailed project information will be shared during the recruitment process.

About the project

This is how we organize our work

This is how we work on a project

• Continuous Deployment
• Continuous Integration

What we offer

• Flexible cooperation model
• Hybrid work setup – remote days available depending on the client’s arrangements - 6 days a week from the office in Kraków
• Collaborative team culture – work alongside experienced professionals eager to share knowledge
• Continuous development – access to training platforms and growth opportunities
• Comprehensive benefits – including Interpolska Health Care, Multisport card, Warta Insurance, and more
• High quality equipment – laptop and essential software provided

Benefits

• sharing the costs of sports activities
• private medical care
• sharing the costs of professional training & courses
• life insurance

Mindbox Sp. z o.o.