T-Hub - AI Agents & LLM Engineer

Description: We are seeking an experienced AI agents & LLM Engineer to join our core development team. You will be responsible for the end-to-end lifecycle of our cutting-edge models - from design and training to integration into customer-facing products. If you thrive on solving complex problems using AI agents & LLMs, possess expert-level Python skills and are driven by delivering tangible production value, this is your opportunity to shape our product innovation. Key responsibilities: - Design, build and deploy solutions based on Machine Learning, LLMs and AI agents with a focus on enterprise production applications - Develop and implement AI-powered applications utilizing RAG, agentic workflows, multi-agent architectures and tool-calling frameworks. - Build and optimize data pipelines for training, validation and inference - Optimize models for performance, scalability and cost-effectiveness - Build scalable and cost-effective AI solutions leveraging cloud-native architectures. - Conduct integration with applications (FastAPI, microservices) - Implement MLOps and LLMOps processes, including automated training, testing, deployment, monitoring, evaluation, guardrails, and model retraining. - Design agent orchestration frameworks and advanced reasoning workflows for autonomous and semi-autonomous AI systems. - Integrate different AI models into production systems working closely with other engineering teams - Collaborate with data science, POs and IT teams to define requirements into implementation - Ensure security, compliance, reliability, and observability of deployed AI solutions. Key competencies: - Minimum 5 years of experience in Software Engineering, Machine Learning, Data Science or AI-related roles. - Strong hands-on experience designing and deploying AI agents and LLM-based applications in production environments. - Deep understanding of Transformer architectures, RAG systems, embeddings, vector databases, prompt engineering, context management and agent orchestration. - Expert-level proficiency in Python and modern AI frameworks. - Strong experience with LangChain, LangGraph, SmolAgents, Google ADK, CrewAI or similar agent frameworks. - Practical knowledge of building autonomous and multi-agent systems. - Experience implementing advanced reasoning patterns, planning strategies and tool-augmented AI workflows. - Strong understanding of software architecture, API development, microservices and distributed systems. - Experience with SQL, data preprocessing, ETL pipelines, feature engineering and large-scale data processing. - Experience with CI/CD pipelines and DevOps practices. - Knowledge of MLflow, Airflow or similar MLOps platforms. - Strong analytical, communication, and problem-solving skills. - Fluent English communication skills, both written and spoken. Nice to Have: - Experience with Generative AI evaluation frameworks and observability platforms (LangSmith, Arize, Galileo, Phoenix, etc.). - Experience fine-tuning open-source models and working with model serving frameworks. - Knowledge of graph-based AI architectures and knowledge graphs. - Experience implementing AI governance, guardrails, and Responsible AI practices. What we offer: - Employment contract - Additional day off on the occasion of birthdays/namedays - Medical package and life insurance - Benefit platform - you choose what you benefit from - Access to training platforms to improve your knowledge - I know Talent - training or money for referring friends to work 😊! - Besides, with us you can count on access to our products and services at preferential terms and benefits, which you will read about below