Staff Applied AI Researcher - Agentic Reasoning Systems (Brazil)

The role

You will define how the platform reasons at runtime and how autonomous systems make trustworthy decisions in production. You will lead research across core runtime intelligence capabilities including task decomposition, agent coordination, and model routing.

What you will do

• Set technical direction for agentic reasoning systems and runtime intelligence
• Architect infrastructure for researcher augmentation at scale
• Advance the science of autonomous reasoning through designing and training learned components
• Unify perception, retrieval, reasoning, and action into coherent agentic workflows
• Drive research on agent reliability for regulated environments
• Define evaluation methodology for runtime intelligence
• Influence platform-level architecture
• Mentor researchers across levels
• Maintain hands-on research impact through technical work, publications, and patents

Required qualifications

• PhD or MSc in Computer Science, Machine Learning, AI, Robotics, or a related field
• 8+ years in AI/ML research with demonstrated impact on production systems
• 3+ years building LLM-based or autonomous AI systems
• Deep hands-on experience in at least two of: multi-agent coordination, planning under uncertainty, sequential decision-making, probabilistic inference, model routing, or tool-using agent systems
• Experience designing evaluation frameworks for systems measuring decision quality, reliability, and failure recovery
• Experience designing and operating research systems that integrate multiple models and data sources in production or near-production settings
• Proficient in Python with strong software architecture instincts
• Experience setting technical direction for a research area, mentoring researchers, and influencing quality standards

Nice to have

• Experience building orchestration systems with non-trivial control flow
• Background in probabilistic modeling, Bayesian inference, control theory, or formal verification applied to ML systems
• Experience with reliability engineering for autonomous AI in regulated environments
• Track record of integrating heterogeneous components into systems
• Strong publication record with evidence of sustained, focused research impact
• Experience taking reasoning or agent systems from prototype to production
• Domain familiarity in energy, semiconductor, finance, aerospace, telecom, or supply chain

About the company

Articul8 provides a platform that combines domain-specific models, autonomous agentic reasoning, reliable model evaluation, and multimodal understanding for regulated industries. The company brings together research, engineering, product, and domain expertise to deliver AI for high-stakes environments.