eMAG

• Participate in migrating on-prem services to the Cloud; • Configure and tune a variety of services in order to increase system stability, performance and security; • Develop, maintain and improve automation for all our systems; • Capacity planning and performance tuning for high traffic events such as Black Friday; • Get involved in designing and implementation of new features; • Troubleshoot issues and provide support for internal teams; • Identify repetitive issues or tasks and focus on automation and implementation of permanent solutions; • Continuous improvement of monitoring and alerting systems.

• Lead the installation, configuration, monitoring, maintenance and troubleshooting of SQL and NoSQL database platforms, including MySQL, PostgreSQL and MongoDB. • Design, implement and maintain highly available and scalable database solutions that support business and technical requirements. • Monitor database performance and proactively identify optimization opportunities. • Administer database servers and optimize operating systems for database workloads. • Define, implement and improve backup, recovery and disaster recovery strategies. • Manage database patching and upgrade processes while ensuring service continuity. • Deploy and maintain physical servers and containerized environments supporting database services. • Develop and maintain automation and configuration management solutions. • Collaborate closely with software development, DevOps and infrastructure teams across multiple business units. • Drive database architecture planning and technical decision-making. • Mentor junior database administrators and share best practices across the team. • Develop and maintain internal procedures, operational documentation and best practices. • Respect internal procedures related to the usage of company tools and equipment.

• Design and ship agentic workflows across the dev lifecycle — auto-documentation, test generation on MRs, parity testing for migrations, review augmentation; • Build reusable platform components: MCP servers, tool integrations, prompt/ orchestration libraries other teams can self-serve; • Own eval & observability for AI flows (Langfuse, LLM-as-judge, regression suites) so outputs are trustworthy, not just impressive demos; • Deploy flows as production services (Docker, K8s) with proper CI/CD and cost/ latency awareness; • Drive adoption at scale — measure impact via developer-productivity metrics (e.g. getDX), iterate on what actually moves throughput and cycle time; • Keep pace with and adapt to the fast-moving agentic landscape — continuously evaluate new tools, models, and patterns, fold the useful ones into how the org works, and bring pragmatic choices.

Role Description Join us as an AI Platform Engineer (AppCompass, Devex & Cloud Enablement Team) to own the AI capabilities layer, working at the intersection of AI infrastructure, developer experience, and platform engineering. - Operate and evolve the centralized LLM Gateway that routes all company AI API traffic (Cursor, Claude Code, Kiro, Toqan, LUMI), with disaster recovery runbooks and SLA enforcement (≥ 99.5% uptime). - Instrument observability through Langfuse — latency, cost per model tier, error rates, and usage patterns. - Enforce AI license and access policies (Cursor seat limits, agentic tool controls) through self-service tooling. - Build RAG pipelines and develop MCP servers. - Track AI adoption across the SDLC and own the AI Skills Marketplace and AI Guilds coordination tooling in Backstage. - Build the Slash AI Assistant — a natural language interface over Backstage and internal tooling. - Own the AI Incident Investigator feature — cross-system analysis across GitLab, Jira, and monitoring through Backstage. - Integrate AI capabilities into the self-service action catalog and productionize agentic workflows (tool-use, multi-step reasoning, agent orchestration). - Maintain audit trails for AI tool usage and data classification compliance. - Build the AI Adoption Best Practices guide and surface it through Backstage. Qualifications - 3+ years of backend or platform engineering experience (TypeScript/Node.js or Python). - Hands-on experience with LLM APIs (OpenAI, Anthropic, Gemini) — building integrations, not just prompting. - Understanding of API gateway patterns, observability, and cost instrumentation. - Familiarity with Docker/Kubernetes and CI/CD (GitLab CI preferred). - Experience with Langfuse, LangChain, or similar LLM observability/orchestration tools. - Experience with MCP (Model Context Protocol) server development. - Agentic workflow design (tool-use, multi-step reasoning, agent orchestration). - Background in developer productivity, DevEx, or platform engineering teams. - Experience with React/TypeScript for frontend plugin development. - Experience building or extending Backstage plugins, or equivalent internal developer portal work. - You think in systems, not features, and you're comfortable navigating the moving target of agentic AI tooling. - You measure your own impact — cost saved, adoption rate, uptime — and document what you build so others can extend it. Benefits - Medical subscription: Medicover or Regina Maria. - A flexible budget that you can invest in yourself as you wish: meal tickets, holiday tickets, cultural vouchers, private pension, foreign language classes, eMAG, Fashion Days, Therme & Genius, membership to different gyms or even professional development classes. - Different discounts from our partners: banking, mobile, dental medicine, or wellness. - Access to the Bookster library and free credits on the Hilio psycho-emotional health platform. - An accelerated learning environment, with access to over 100,000 curated online resources and platforms, learning academies, and development programs. - New headquarters, where sleek design, natural light, and versatile spaces create an energizing and comfortable environment for hybrid work.