AI Engineer (SINGU Platform)

SINGU • Paris Township, MI

16d • $16,600 - $27,000 • Hybrid

About The Position

We are looking for an AI Engineer who builds AI features that actually ship — reliable, observable, and maintainable in a live product.
You will be the first dedicated AI Engineer on the team, owning technical decisions around AI integration — from model selection and deployment to observability and safety guardrails.
This is a hybrid role based in Kraków — 2–3 days per week from the office.

Requirements

• 1+ year of commercial experience delivering AI/LLM features in production environments.
• 5+ years programming experience.
• Solid understanding of LLM deployment patterns — RAG, tool use, agents, streaming — and their trade-offs.
• Practical experience with prompt engineering, prompt chaining, and evaluation frameworks.
• Experience building AI guardrails and observability pipelines (input/output validation, latency tracking, cost monitoring).
• Experience evaluating trade-offs across cost, latency, quality, and operational complexity.
• Strong TypeScript skills.
• Understanding of REST API design and integration patterns in distributed SaaS systems.
• Deep understanding of LLM tool-use patterns and agent-to-service communication — including protocols such as MCP.
• Professional working proficiency in English — technical documentation, async collaboration, and cross-team discussions.

Nice To Haves

• Ability to read and understand PHP — our core backend is PHP-based; AI features integrate via REST APIs.
• Experience participating in AI-driven refactoring or automation initiatives within engineering teams.
• Background in enterprise software or multi-tenant SaaS environments.

Responsibilities

• Design and implement AI integrations within our existing SaaS product, ensuring reliability, scalability, and production readiness.
• Design AI pipelines and integration patterns for LLM-based features.
• Build guardrail and observability systems to ensure LLM outputs are safe, consistent, and auditable — including prompt validation, output filtering, and monitoring via tools like Langfuse.
• Lead MCP (Model Context Protocol) integration across the architecture in a Server-Client model, collaborating with platform and backend engineers.
• Evaluate and select AI models with a structured analysis covering inference cost, latency, accuracy, and vendor trade-offs.
• Define and implement evaluation frameworks for testing AI features — covering correctness, performance, regression, and business alignment.
• Maintain and iterate on LLM infrastructure — including key management, multi-vendor proxying, and model lifecycle management.
• Document AI architecture decisions and contribute to engineering-wide knowledge sharing.

Benefits

• Competitive Salary Range: depending on your experience, we offer between 20'000 - 27'000 PLN net on a B2B contract, or between 16'600 – 22'410 gross on Contract of Employment.
• Impact at Scale: Help shape the operational backbone of a high-growth SaaS company with global reach and clients like Prologis, CBRE, Unibail-Rodamco-Westfield, Auchan, Savills, NEPI Rockcastle and Logicor.
• Category Leadership: Be part of the #1 PropTech brand in facility, maintenance, and ESG management.
• Organic and M&A Growth: M&A is a big part of our plans and we are on a mission to consolidate our space to create a European Champion
• Collaborative Culture: Work alongside a curious, international, and mission-driven team that values learning, ownership, and giving back.
• Flexibility & Autonomy: Hybrid working model, annual learning budget, office-led social initiatives (e.g. yoga, soccer, company retreats, happy hours, Wednesday breakfasts) and the freedom to drive initiatives.
• Attractive Employment Terms: Competitive compensation, flexibility between Full Time Employment and B2B contract and exciting intra-company career growth path.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed