Senior AI / LLM Research Engineer

About the project

At Trilagi, we're tackling one of the most persistent challenges in modern IT operations: understanding why systems fail. Our research project is building an intelligent diagnostic system that revolutionize cloud platform operations through generative AI solutions.

You'll be working on cutting-edge research that bridges computational linguistics and distributed AI systems. We're developing novel approaches that address fundamental gaps in current scientific knowledge:

• Advanced semantic processing of heterogeneous technical data

• State-of-the-art hierarchical multi-agent architectures enabling complex task orchestration

This is genuinely novel research - we're creating the mathematical foundations and algorithms that don't yet exist in academic literature or commercial products.

This isn't purely academic research. You'll see your work evolve from mathematical models through experimental validation to a working prototype tested on real data from production environments. Your research will be published in conferences, and the resulting system will be deployed commercially.

You'll have the creative freedom to explore multiple approaches, the resources to test ambitious ideas, and the satisfaction of contributing both to scientific knowledge and practical solutions that teams will use every day.

Your responsibilities

• Lead scientific design and execution of research on adaptive data processing and multi-agent communication systems

• Design and implement novel algorithms for processing heterogeneous technical data

• Develop custom evaluation metrics adapted to diagnostic contexts

• Conduct rigorous experimental validation of different approaches

• Perform comprehensive statistical analysis of research outcomes

• Design hierarchical agent architectures and communication protocols

• Develop algorithms dedicated for diagnostic reasoning

• Optimize LLM integration and utilization patterns

• Implement hallucination reduction mechanisms

• Define diagnostic effectiveness metrics and benchmarks

• Ensure model stability and reliability in production-like conditions

• Optimize inference speed and computational efficiency

• Fine-tune integrated system components

Our requirements

• MSc or PhD in Computer Science, Mathematics, Statistics, or related field

• Hands-on experience with multi-agent systems or agent frameworks

• Understanding of chunking strategies, semantic fragmentation and embedding models

• Experience with Retrieval-Augmented Generation (RAG) systems

• Experience with prompt engineering and LLM fine-tuning

• Knowledge of vector databases (Pinecone, Weaviate or Qdrant)

• Proficiency in Python with scientific computing and LLM tech stack (e.g. LangChain, LangGraph, AutoGen, CrewAI, MCP, Pandas, NumPy, scikit-learn, spaCy, TensorFlow/PyTorch)

• Strong background in machine learning and deep learning

• Scientific publication record

• Good command of Polish and English

Optional (Nice to have)

• Experience with cloud platforms (AWS, GCP, Azure)

• Successfully deployed LLM-based systems in real-world applications

• Published research on LLMs, RAG systems, or multi-agent architectures

• Familiarity with IT diagnostics, observability, system logs, or technical troubleshooting

• Demonstrated ability to solve novel problems with no existing solutions

• Cross-functional skills: Bridge research and practical engineering

What we offer

• Fully Remote: Work from anywhere in Poland

• Research Autonomy: High degree of independence in experimental design and methodology

• Small Expert Team: Direct collaboration with research leaders, minimal bureaucracy

• Startup Mentality: Fast decision-making, open communication, impact-focused culture

• Modern Infrastructure: Access to cloud computing resources, latest AI tools and frameworks

• Cutting-edge research: Work on unsolved problems at the frontier of AI applications

• Scientific impact: Co-author publications in journals or conferences