Teams at Fabrion

Lead the Agentic AI Lab’s full-cycle research agenda, including model and training design, data, evaluation, benchmarking, deployment, and publication. Train specialized enterprise models, define rigorous evaluation gates, move research from public benchmarks to customer shadow deployments, and build a small multidisciplinary team. The role partners closely with founders and platform engineers while establishing research direction, documenting technical decisions, and mentoring engineers into researchers.

Build and operate secure, scalable ML pipelines and hybrid GPU infrastructure for training, fine-tuning, serving, and governing open-source LLMs and agentic apps. Implement CI/CD, model versioning, observability, benchmarking, security controls, and integration with RAG/agent tools and vector DBs to support production deployments across tenants.

Research, evaluate, and manage partnerships with data providers. Assess datasets for coverage and interoperability, support deal structuring, maintain partnership pipeline, and collaborate with product, engineering, and legal to integrate data into the platform.