AI Solutions Engineer

Mindbox is a tech-driven company connecting top IT talents with technology projects for leading enterprises across Europe. They specialize in consulting, engineering, and digital solutions delivery.

• Proven software-engineering background delivering production services and automation in operational environments.
• Hands-on experience with observability and operational data (logs, metrics, traces, alerts) to prioritise engineering-driven improvements.
• Strong programming and scripting skills, preferably in Python, with expertise in APIs, webhooks, and event-driven architecture.
• Demonstrated DevSecOps mindset with continuous integration and delivery practices.
• Skilled at building production-ready tooling with monitoring, audit trails, and supportability.
• Experience navigating complex organisations and driving delivery across multiple teams.
• Practical Agile delivery knowledge, especially Scrum or Kanban.
• Fluent English communication skills.
• Experience implementing AI or Generative AI solutions for operations, including retrieval-augmented generation and incident/change-risk assistants.
• Understanding of Responsible AI including human-in-the-loop design, auditability, and AI incident response.
• Ability to publish engineering standards, reference implementations, and automation golden paths for organisation-wide reuse.

Nice to have:

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

• 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 including monitoring, ITSM, knowledge bases, and configuration sources, ensuring least-privilege, proper audit, and resilient error handling.
• Define measurable success indicators and instrument solutions to capture demonstrable impact.
• Build reusable AI patterns for data redaction, grounding and citation, evaluation, monitoring, and runbook standards.
• Drive production governance including 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 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 outcomes.