At Trilagi, were 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.
Youll be working on cutting-edge research that bridges computational linguistics and distributed AI systems. Were developing novel approaches that address fundamental gaps in current scientific knowledge:
Advanced semantic processing of heterogeneous technical data
This is genuinely novel research—were creating the mathematical foundations and algorithms that dont yet exist in academic literature or commercial products.
This isnt purely academic research. Youll 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.
Youll 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.
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
requirements-expected :
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 (Pandas, NumPy, scikit-learn, Transformers, TensorFlow/PyTorch, LangChain, etc.)
Strong background in machine learning and deep learning
Familiarity with IT diagnostics, observability, system logs, or technical troubleshooting
Scientific publication record
Good command of Polish and English
offered :
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
