Research Engineer - Trustworthy AI & Production NLP

Within the Agorai Innovation Hub we are looking for a talented and proactive resource, who will work directly with the AI Architect and Head of Technology on use case definition and technical direction.

The researcher will work at the intersection of language understanding, knowledge representation, and trustworthy AI. This means combining LLMs with structured knowledge to ground reasoning; designing evaluation frameworks that surface failure modes before they reach production; and building information extraction systems whose outputs can be audited.

Key responsibilities

• Own the research-to-production arc on language understanding and knowledge-grounded AI: from literature review and experimentation to deployment and monitoring;
• Design AI systems whose outputs can be explained, audited, and trusted in regulated contexts — and know when simpler approaches serve that goal better than complex ones;
• Build production-quality services around your models: APIs, inference pipelines, evaluation harnesses;
• Design evaluation frameworks that go beyond benchmark metrics — testing for failure modes, edge cases, and behavior under distribution shift;
• Work on information extraction, semantic understanding, and structured knowledge problems grounded in real industrial data;
• Stay current with the research frontier in language models, interpretability, and trustworthy AI;
• Contribute to technical standards and code quality across the team;
• Work on a genuinely hard and open research problem with direct industrial application.

Requirements

• Master's degree or PhD in Computer Science, Artificial Intelligence, Data Science, Engineering or a related STEM field;
• At least 3–5 years of experience working with NLP or language understanding systems in production environments, such as text classification, information extraction, semantic search, RAG, or generative systems;
• At least 3–5 years of experience in applied NLP or computer vision, working with real-world data and operational constraints rather than benchmark-only environments;
• Experience working across one or more of the following sectors: Healthcare, Financial Services, Mobility/Transport, Agriculture.

Technical Skills

• Fluent across the stack: LLM-based systems, classical ML, APIs, microservices, inference optimization;
• Strong software engineering fundamentals: your code is modular, testable, and maintainable by someone other than you;
• Comfort with the full arc from prototype to production: you know what a model registry is, you have thought about inference latency, you have monitored a deployed model;
• Working knowledge of Python ML ecosystem: PyTorch or JAX, HuggingFace, experiment tracking (MLflow, W&B), serving frameworks.

Soft Skills & Personal Attributes

• Entrepreneurial mindset: takes ownership, operates with autonomy and drives things forward without waiting for direction;
• Genuine interest in trustworthy and explainable AI — not as a theoretical topic but as a design constraint that shapes how you build;
• Excellent communication and stakeholder management skills; able to interact effectively with both technical teams and C-suite executives or institutional clients.

Languages

• English: Full professional proficiency required (primary working language for international projects and publications);
• Italian: Knowledge of Italian is considered an advantage.

Location: Trieste, Italy