Explore AI research as a Co-op Research Engineer at Themis Intelligence, focusing on LLM behavior in real-world applications. This position offers a 12-month opportunity to apply AI principles in a practical environment.
We are looking for an innovative thinker to assist in the post-training lifecycle of Themis Agents. Candidates should have a background in Computer Science, Engineering, or related fields, with an eagerness to learn about AI evaluations and impact. Key projects include analyzing grounding failures and developing evaluation frameworks to enhance model reliability.
Key Responsibilities:
• Evaluate Themis Agents for factual correctness and consistency
• Conduct experiments on prompt engineering and retrieval strategies
• Score and compare model outputs across tasks
• Extend evaluation pipelines using frameworks like LangChain
• Organize and visualize test results effectively
Requirements:
• Enrollment in a Bachelor's degree program in a relevant...