Research Associate - LTI - School of Computer Science

Carnegie Mellon University • Pittsburgh, PA

21h • Onsite

About The Position

Carnegie Mellon University is a private, global research university that stands among the world’s most renowned education institutions. With ground-breaking brain science, path-breaking performances, creative start-ups, big data, big ambitions, hands-on learning, and a whole lot of robots, CMU doesn’t imagine the future, we invent it. If you’re passionate about joining a community that challenges the curious to deliver work that matters, your journey starts here! The Language Technologies Institute (LTI) at CMU is a world-renowned research and education hub at the forefront of natural language processing, machine learning, artificial intelligence, and human-computer interaction. Established within the School of Computer Science, LTI pioneers innovative ways to understanding, processing, and generating human language in both written and spoken forms. We are seeking a Research Assistant. This position will execute the research project "Training LLMs as SWE Agents using Intermediate Rewards". The primary purpose of this position is to develop and train Large Language Model (LLM) agents to solve software engineering tasks by solving the "cold-start" problem in Reinforcement Learning (RL). Flexibility and cultural sensitivity are valued proficiencies at CMU. Therefore, we are in search of a team member who can optimally get along with a varied population of diverse audiences. We are looking for someone who shares our values and who will support the mission of the university through their work.

Requirements

• Bachelor's Degree in Computer Science, Computer Engineering, AI or a related field.
• Experience with Python programming and Deep Learning frameworks (PyTorch).
• Experience with Large Language Models (LLMs) and Reinforcement Learning frameworks such as Areal or SkyRL.
• Familiarity with coding agentic frameworks (e.g., OpenHands, SWE-Agent) and software engineering benchmarks (e.g., SWE-Bench).
• A combination of education and substantial experience from which comparable knowledge is proven may be considered.
• Successful background check investigation may be required

Responsibilities

• Engineering intermediate reward mechanisms
• Integrating them into RL frameworks (such as Areal or SkyRL) using the OpenHands agent framework
• Conducting extensive evaluation on benchmarks like SWE-Bench Verified and SWE-Gym to improve agent training efficiency and performance.
• Design, implement, and execute machine learning experiments to test research hypotheses.
• Collect, process, and analyze experimental data to generate accurate performance metrics and visualizations.
• Collaborate with faculty advisors and research teams to refine methodologies and interpret results.
• Assist in the preparation of academic papers, technical reports, and presentations for conferences or journals.

Benefits

• Benefits eligible employees enjoy a wide array of benefits including comprehensive medical, prescription, dental, and vision insurance as well as a generous retirement savings program with employer contributions.
• Unlock your potential with tuition benefits, take well-deserved breaks with ample paid time off and observed holidays, and rest easy with life and accidental death and disability insurance.
• Additional perks include a free Pittsburgh Regional Transit bus pass, access to our Family Concierge Team to help navigate childcare needs, fitness center access, and much more!
• For a comprehensive overview of the benefits available, explore our Benefits page.

What This Job Offers

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