Profil: AI Engineer 

What we need 

We are seeking a Senior AI Engineer who combines strong software engineering fundamentals with hands-on experience building production GenAI solutions, including agentic workflows and Retrieval-Augmented Generation (RAG). 

• This is an engineering and orchestration role focused on integrating LLM capabilities into enterprise systems - not a traditional model-training/ML research role. 
• 5+ years of professional software development experience (ideally 7+ years across backend/API/integration and cloud platforms). 
• Proven ability to ship production-grade LLM applications (RAG, tool/function calling, agent orchestration) with reliability, security, and observability. 
• Strong ownership mindset and passion for AI engineering - curiosity, experimentation, and a drive to continuously improve the product and the team. 
• Excellent communication and collaboration skills; ability to guide, mentor, and unblock other engineers as we build out an AI engineering capability. 

Offer:  

• Location: 100% remote
• Start: ASAP 
• Employment: B2B contract with apreel 
• Rate: 120- 175 zł/h + VAT (do negocjacji w zależności od doświadczenia) 

Required Skills, Experience, and Attitude 

• Strong software engineering background (not a research-only data science profile): designing, building, and operating production systems. 
• Proficiency in at least one backend language used for AI systems (Python preferred) and comfort integrating with enterprise stacks (C#/.NET is a plus). 
• Hands-on experience building and integrating RESTful APIs; GraphQL experience is a plus. 
• Strong understanding of distributed systems fundamentals: concurrency, async I/O, resiliency/retries, rate limits, caching, and performance optimization. 
• Experience with RAG systems: document ingestion pipelines, chunking/metadata, embeddings, retrieval strategies, grounding, and evaluation. 
• Experience with agentic frameworks and orchestration concepts (planning, routing, tool use, human-in-the-loop interruptions). Frameworks may include LangGraph, LangChain, Microsoft Semantic Kernel, or equivalent. 
• Understanding of LLM application quality and safety: evaluation approaches, hallucination mitigation, prompt/version management, and guardrails for sensitive data. 
• Experience working with model platforms (e.g., Azure OpenAI/OpenAI or similar) and designing for reliability (timeouts, fallbacks, quotas).