Senior AI Engineer (LLMs / RAG / Real-Time Systems)

Senior AI Engineer

💰 Salary: 28 000 – 31 000 PLN net/month (B2B) + 26 days paid annual leave + equity (ESOP)📍 Location: Remote (Poland) + meetup in Poznań once per monthAbout the Project

Our client is an early-stage startup building a real-time AI platform that supports professionals during live conversations. The system processes conversations in real time and provides contextual insights, knowledge retrieval, and guidance during live interactions. The team combines experience in AI systems, distributed infrastructure, and SaaS, and is now scaling engineering to bring the product to early users.

Role

The client is looking for a Senior AI Engineer / AI Scientist who can combine research-level thinking with production execution. You will work on the core intelligence layer, reasoning over live conversations, prompt orchestration, knowledge retrieval, and experimentation frameworks. This role is ideal for someone who enjoys turning complex ideas into reliable, real-world AI systems.

Responsibilities

• Build and improve LLM-powered systems

• Design prompt orchestration and reasoning pipelines

• Develop retrieval and grounding approaches (RAG)

• Create experimentation frameworks for evaluating AI behaviour

• Analyse outputs using quantitative and qualitative metrics

• Translate research ideas into production-ready systems

• Collaborate on AI architecture and system design

Requirements

• MSc or PhD in Computer Science, Mathematics, Physics, or similar

• Strong understanding of AI/ML concepts and system design

• Ability to write production code in Python, TypeScript, or similar

• Experience with LLMs / prompt engineering

• Strong analytical and problem-solving skills

• Experience designing experiments and evaluation frameworks

• Fluent English

• Comfortable working in a remote environment

Nice to Have

• Experience with RAG systems or conversational AI

• Familiarity with LangChain or similar frameworks

• Knowledge of real-time / streaming systems

• Understanding of latency, reliability, and system trade-offs

• Experience with AI systems in production

What the Client Offers

• Opportunity to build core AI systems from an early stage

• Real impact on how AI behaves in production

• Work with experienced founders and engineers

• Remote-first environment

• Competitive compensation + equity

• High level of ownership and autonomy

• Culture focused on quality, rigor, and real-world impact

Ideal Profile

• Thinks scientifically but builds pragmatically

• Cares about correctness, explainability, and reliability

• Enjoys experimentation as much as implementation

• Comfortable working at the intersection of research and product