Applied AI Engineer - Poland

Inviso; Kraków; Remote; PLN 180,000 - 240,000; Full time

Job summary

Inviso partners with a client to hire an experienced Applied AI Engineer focused on production-grade AI capabilities. You will own the design and operation of AI features across an enterprise platform, including agent runtimes, model routing, RAG, tool calling, guardrails, evaluation, monitoring, and cost management.

The role emphasizes moving from prototype to monitored production systems, evaluating AI behavior, and collaborating with product, engineering, and security teams to deliver value

Qualifications

• Experience shipping software backed by LLMs, ML models, or agentic workflows to production environments.
• Ability to design or implement agent runtime, orchestration, model routing, tool calling, or AI workflow patterns.
• Strong understanding of RAG, grounding, retrieval quality, prompt design, and evaluation approaches.
• Experience building evaluation harnesses, golden sets, regression checks, or measurable AI performance frameworks.
• Must treat cost, latency, reliability, and safety as engineering constraints.

Responsibilities

• Ship AI capabilities that operate in production, not demos.
• Evaluate AI behavior rigorously and partner with product and engineering teams on decisions about AI implementations.
• Collaborate with backend, platform, product, and security teams to deliver robust AI features.
• Monitor production AI behavior and improve systems based on evidence.
• Communicate and collaborate effectively in client-facing consulting environments.

Skills

LLM-based software design

Agent runtime

RAG systems

Cost & latency optimization

Production AI monitoring

Cross-functional collaboration

Client-facing consulting

Value-driven shipping

Tools

Model routing frameworks

Tool calling

AI security tooling

Job description

Inviso is partnering with one of our clients to find an experienced Backend / Platform Engineer to join their team working remotely. Inviso is managing the recruitment and placement process for this opportunity. This is a remote, direct-hire permanent employee position for our client that is a global multi-billion dollar software conglomerate.

The Applied AI Engineer is responsible for building and operating AI capabilities across an enterprise platform, including agent runtimes, model routing, RAG, tool/function calling, guardrails, evaluation, monitoring, cost management, latency optimization, and production quality controls.

This role is focused on shipping AI that works in production, not demos. The ideal candidate understands how to move from prototype to monitored production systems, can evaluate AI behavior rigorously, and can partner with product and engineering teams to decide when AI is the right solution and when it is not.

Experience & Skills Required

• Experience shipping software backed by LLMs, ML models, RAG systems, or agentic workflows to real production users.
• Experience designing or implementing agent runtime, orchestration, model routing, tool/function calling, or AI workflow patterns.
• Strong understanding of RAG, grounding, retrieval quality, prompt design, context management, and evaluation approaches.
• Experience building evaluation harnesses, golden sets, regression checks, quality gates, or measurable AI performance frameworks.
• Ability to treat cost, latency, reliability, and safety as first-class engineering constraints.
• Experience building guardrails and controls for AI systems, including untrusted retrieved content, tool output risk, and failure modes.
• Experience monitoring production AI behavior and improving systems based on evidence, not opinion.
• Strong software engineering skills and ability to collaborate with backend, platform, product, and security teams.
• Strong communication and collaboration skills for client-facing consulting environments.
• Pragmatic mindset with the ability to prioritize business value and ship useful AI capabilities quickly and responsibly.

Desired Qualifications

• Experience with Claude, GPT, Azure OpenAI, open-source models, model routing, fine-tuning, distillation, or small/edge models.
• Experience with MCP, A2A, multi-agent orchestration, AI tool calling, or agent evaluation.
• Experience with LLM-as-judge approaches calibrated against human evaluation.
• Experience with semantic knowledge management, ontologies, knowledge graphs, or semantic layers.
• Experience with AI development lifecycle practices across data, build, evaluation, deployment, monitoring, and continuous improvement.
• Experience using AI-assisted development tools while maintaining strong review, testing, and safety discipline.

Success Criteria

Success in this role is measured by the ability to deliver AI capabilities that are useful, reliable, measurable, safe, and cost aware. Applied AI Engineers are expected to turn experiments into production features, build evaluation discipline into the delivery process, and help client teams make informed decisions about where AI creates real value.