ai engineer for scientific knowledge

Iris.ai builds an agentic AI platform that scales expert-level domain knowledge across organizations. Its products support the GenAI lifecycle, including data ingestion, RAG and indexing pipelines, agentic orchestration and reasoning, and LLM evaluation and governance.

• Own the full development lifecycle, from idea and architecture through implementation, testing, and delivery of AI products;
• Design and build robust AI systems, including proprietary RAG pipelines and LLM evaluation frameworks used by leading R&D teams;
• Drive innovation by testing new approaches and bringing AI research into production;
• Collaborate with researchers, product managers, and engineers to shape and ship features;
• Build scalable, testable, maintainable systems for performance and reliability;
• Contribute to transforming how people interact with scientific knowledge and applied AI;
• Contribute meaningfully within a distributed, deep-tech team;
• Keep learning and develop as an AI engineer with support, mentorship, and resources.

• 5+ Years of software development experience, including 3+ years with Python;
• Solid experience with web backends (Django/Flask), REST APIs, databases, and cloud infrastructure;
• Familiarity with ML systems or motivation to learn them in depth;
• Ability to work in a collaborative environment;
• Proficiency in English;
• Nice to have: an advanced degree in Computer Science or a related field, previous work with LLMs, NLP, or AI model evaluation, experience contributing to or using RAG systems in production, open-source contributions, academic research, or mentoring.

• Compensation is typically 25% above local market averages and is reviewed annually;
• All colleagues receive ownership through the company’s 3% ESOP pool;
• 30 Days of paid vacation;
• 5 Additional paid vacation days for Learning and Development;
• Private health insurance with premium coverage and bi-annual health checks;
• Free MultiSport card or fitness subscription coverage;
• Flexible hours;
• Personal annual learning budget for conferences, courses, or certifications;
• Personal equipment budget;
• Charity and volunteer activities;
• Seasonal working camps and team retreats;
• Weekly tech deep dives, mentorship, pair coding, and knowledge-sharing.