Staff AI Engineer – AI Infrastructure, Agentic Platform

This is a fully remote position, open to applicants in Poland.

📋 Description

• Enhancing the AI knowledge platform by advancing the retrieval, indexing, and synthesis layer (currently utilizing semantic RAG, re-ranking, and HyDE) into an organization-wide solution that supports both internal engineering tools and customer-facing functionalities.

• Designing and managing agentic infrastructure on AWS, comprising multi-step, tool-utilizing AI systems that strategize, retrieve, and act on intricate queries and operational events, with cost control and observability integrated from the outset.

• Developing and constructing graph-based, relationship-aware retrieval across the organization's data repositories, facilitating multi-hop queries and enabling agents to accumulate organizational knowledge over time. This initiative is on our roadmap and not yet in production—you will shape the methodology.

• Collaborating with product engineering to determine the AI platform API surface, converting infrastructure primitives into developer-ready abstractions.

• Creating reference agent implementations on the platform for operational incident triage, customer support, and future agentic applications—rooting each agent's reasoning in institutional knowledge.

• Managing the AI infrastructure cost model by tracking compute, model, and storage expenditures, identifying anomalies, and suggesting guardrails to ensure workloads remain within established budgets.

⛳️ Requirements

• Over 7 years of professional software engineering experience, including a minimum of 2 years in developing and operating production AI/LLM application systems—focusing on real-world implementations rather than research, prototyping, or demonstrations.

• Advanced retrieval engineering skills beyond the fundamentals. Our technology stack already incorporates re-ranking and HyDE; we require someone with experience at or above this level: hybrid search, re-ranking, query transformation, context-window management, and assessment of retrieval quality in a production setting.

• Practical experience with agentic frameworks and multi-step reasoning loops—focusing on tool usage, iteration control, cost governance, and model routing trade-offs.

• Fluency in production-grade software engineering (strict typing, testing, async/concurrency, modern toolchain) in Go, Python, or TypeScript, with the capability to quickly adapt to another language.

• Direct experience managing AI workloads on a cloud-based AI platform (AWS Bedrock or Azure AI Foundry), including knowledge of the identity/secrets model and model access governance. Preference for Bedrock due to our AWS stack.

• Proficient in Terraform, with the ability to independently author and provision new infrastructure rather than merely modifying existing modules.

• Familiarity with production observability for AI systems, including metrics, structured logging for model expenditure and latency, and evaluation frameworks to identify regressions.

• Awareness of HIPAA-style data-handling requirements within a regulated SaaS environment. Previous experience in healthcare is advantageous but not essential.

🏝️ Benefits

• Additional vacation days to enhance work-life balance.

• A thoughtfully crafted private medical package to prioritize your well-being.

• A sports card to support your active lifestyle.

• Life and accident insurance for your peace of mind.

• A modern office located in Warsaw’s Powiśle district, featuring views of the Vistula River, recreational amenities, and excellent nearby dining options.

• A high-growth, welcoming, and engaging work environment with ample opportunities for career advancement.