Georgia Tech researchers Jennifer Kim and Mark Riedl have received a $500,000 grant from the National Science Foundation to develop large language models (LLMs) aimed at providing strength-based job coaching for autistic job seekers. The project involves collaboration with Heather Dicks, a career development advisor in Georgia Tech’s EXCEL program, as well as other nonprofit organizations that support autistic individuals in their job search.
According to Dicks, people with autism often face long periods of unemployment, with job searches lasting three to six months in favorable economic conditions and up to 18 months when the economy is weaker. She noted that limited availability of human job coaches leads to long waitlists at nonprofits serving neurodivergent populations. Dicks believes that AI tools could help fill this gap by offering immediate support.
“These organizations often run at a slow pace, and there’s high turnover,” Dicks said. “An AI tool could get the job seeker quicker support. Maybe they don’t even need to wait on the government system.
“If they’re on a waitlist, it can help the user put together a resume and practice general interview questions. When the job coach is ready to work with them, they’re able to hit the ground running.”
Kim specializes in technology designed for neurodivergent users, while Riedl focuses on artificial intelligence and machine learning. Their research aims to identify challenges faced by autistic individuals during their job search and determine how coaching can improve employment outcomes.
“Large-language models have an opportunity to support this kind of work if we can have more data about each different individual strength,” Kim said.
“We want to know what worked for them in specific settings at work, what didn’t work, and what kind of accommodations can better help them. That includes how they should prepare for interviews, how they can better represent their skills, how they can address accommodations they need, and how to write a cover letter. It’s a broad range.”
Dicks highlighted that interviews are particularly challenging for people with autism due to difficulties interpreting nonverbal cues or understanding subtle hints within questions.
“They have trouble picking up on visual and nonverbal cues — the tone of the interview, figuring out the nuances that a question is hinting at,” she said. “They’re not giving the warm and fuzzy vibes that allow them to connect on a personal level.”
Kim explained why focusing on strengths is important: “The issue is that they don’t know how these strengths can be applied in the workplace,” she said. “Once they understand this, they can communicate with employers about their strengths and the accommodations employers should provide to the job seeker so they can successfully apply their skills at work.”
She also emphasized supporting candidates through rejection: “When you get a lot of rejection emails, it’s easy to feel you’re not good enough,” Kim said. “Being constantly reminded about your strengths and their prior successes can get them through the stressful job-seeking process.”
Dicks added that feedback from LLMs could help candidates improve over time: “It can tell them what would’ve been a better answer or a better way to say it,” she said. “It can also encourage them with reminders that you get 100 noes before you get a yes.”
Support does not end after hiring; government-contracted coaches may assist clients for up to 90 days post-employment but sometimes this period is insufficient due to longer company probationary periods or ongoing needs for accommodation.
“I could see these models evolving to being supportive at those critical junctures of the probationary period being over or the one-year job review or the annual evaluation that everyone dreads,” Dicks said.
Dicks currently supports around 15 students through Georgia Tech’s EXCEL program—a mentorship initiative assisting students with intellectual and developmental disabilities throughout their academic journey and into employment.
