AI Platform Engineer

Recruitment for

About the project

Your responsibilities

• Own AI platform deliverables from initial problem definition through implementation, production launch, adoption, and ongoing improvement.
• Design, build, and maintain platform capabilities such as LLM gateways, retrieval systems, agent workflows, evaluation frameworks, and developer tooling.
• Define measurable success criteria and service-level objectives (SLOs), using production metrics to guide improvements.
• Build reliable, observable, and resilient systems with predictable failure handling and effective incident management.
• Develop clean interfaces, documentation, reference implementations, and migration paths to make platform adoption straightforward.
• Design secure AI execution environments with appropriate permissions, tenant isolation, auditability, and access controls.
• Apply distributed systems principles, including consistency, idempotency, concurrency management, and resilience.
• Participate in on-call rotations, respond to production incidents, and implement improvements based on post-incident reviews.
• Collaborate with Engineering, Product, Security, Infrastructure, SRE, and Developer Experience teams.
• Establish reusable technical standards and best practices for building and operating production-ready AI systems.
• Use AI coding tools and coding agents effectively, ensuring their output meets engineering and quality standards.

Our requirements

• Practical experience building or operating production AI systems, such as retrieval platforms, LLM applications, agent systems, or AI developer tools.
• Strong software engineering fundamentals and experience designing and operating distributed systems.
• Understanding of reliability, concurrency, idempotency, consistency, failure modes, and secure multi-tenant architectures.
• Knowledge of AI system evaluation, retrieval quality, agent reliability, and the trade-offs between quality, latency, and cost.
• Experience with observability, monitoring, measurable success criteria, and operational targets such as SLOs.
• Understanding of secure AI execution, including least-privilege access, permission management, auditability, and policy enforcement.
• Experience taking a technical solution from initial concept to production and remaining accountable for its performance and adoption.
• Ability to troubleshoot production issues, participate in incident response, and drive continuous improvement.
• Experience using AI coding tools while independently reviewing and validating generated code.
• Strong communication and collaboration skills, with the ability to explain complex technical concepts to different stakeholders.
• A customer-focused mindset and an interest in building reusable capabilities that help other engineering teams work more efficiently.

Optional

• Experience with LLM gateways, RAG, agent frameworks, AI evaluation systems, or internal AI platforms.
• Familiarity with OpenTelemetry, distributed tracing, and AI observability.
• Experience with FinOps, AI cost optimization, or usage-based cost monitoring.
• Knowledge of application security, identity and access management, and policy enforcement.
• Experience with search, ranking, relevance evaluation, or experimentation.
• Background in internal developer platforms, multi-tenant infrastructure, SDKs, or developer enablement.
• Familiarity with API gateways, routing systems, service orchestration, or workflow engines.

What we offer

• Open PTO policy for eligible employees.
• Quarterly company-wide Days of Disconnect.
• Parental leave and pet-related leave.
• Quarterly fitness reimbursement.
• Medical, dental, and vision coverage.
• Employee Assistance Program (EAP).
• Calm App subscription for the employee and eligible dependents.
• Contract of employment up to 310 000 PLN gross/year