Research Engineer – AI

Primary

2d • Onsite

About The Position

Primary is building the infrastructure to change the recognition, audience, and rewards that journalists receive. Primary Index is the first AI-native ranking system for journalism, serving as the credibility standard for news in the AI economy. The company evaluates individual journalists based on the accuracy, depth, and craft of their published work using a purpose-built AI and a transparent methodology. The role involves designing, building, evaluating, and deploying next-generation AI systems for automated knowledge acquisition and evaluation, working closely with the Chief Scientist on research spanning large language models, automated reasoning, knowledge acquisition, and high-throughput AI systems. The focus is on inventing, implementing, and evaluating new AI approaches rather than applying existing techniques. Current projects include large-scale local inference over text corpora, AI systems for assessing factuality and source quality, faithful explanation generation, large-scale evaluation of journalism, adaptation of open-weight language models, and new methods for evaluating and improving AI systems. This is a research-oriented role emphasizing technical judgment, problem-solving, and independent research. The company values intellectual independence and ambition, seeking researchers who can tackle loosely specified problems, identify key research questions, formulate new approaches, and critically evaluate evidence. Strong reasoning, rapid learning, and sound technical judgment are prioritized over specific software framework familiarity.

Requirements

• A strong background across artificial intelligence, machine learning, or computational cognitive systems.
• The ability to independently design and build sophisticated AI systems.
• Excellent analytical and experimental skills.
• The ability to rapidly understand and extend new research.
• Strong technical judgment and intellectual independence.
• Excellent written and spoken communication.

Nice To Haves

• A PhD is desirable but not essential. Outstanding candidates with an MSc or equivalent experience are encouraged to apply.
• Evidence of suitability includes one or more of: first-author or substantial contributor research publications; substantial AI research projects; open-source AI software; novel machine learning methods; significant technical contributions to research systems; demonstrated ability to rapidly understand and extend unfamiliar AI systems.
• Outstanding candidates will be able to take a broad research direction and independently formulate promising approaches, identify relevant prior work, design appropriate experiments, build and evaluate candidate systems, interpret results critically, and recommend the most promising direction.

Responsibilities

• Translate high-level research ideas into working AI systems.
• Identify relevant literature and implement or extend state-of-the-art methods.
• Design and carry out experiments to evaluate alternative approaches.
• Develop new algorithms, objectives, and evaluation methods where appropriate.
• Effectively employ and critically evaluate AI-based software development tools.
• Build robust, scalable research prototypes.
• Communicate results clearly through technical reports and research papers.

Benefits

• Comprehensive benefits, including health, dental, and vision
• Meaningful equity grants
• An annual performance bonus

What This Job Offers

• Job Type: Full-time
• Career Level: Senior