About this job
The TMW Center
We are a non-profit startup incubated at the University of Chicago’s TMW Center for Early Learning + Public Health, and in partnership with Schmidt Futures. The team is rapidly growing and looking for talented individuals who enjoy building high-quality products for early childhood development. If you’re excited to develop technology for social good, come join us!
The team’s mission is to give all children an equal opportunity to reach their fullest cognitive potential. Research shows that the most critical window for a child’s brain development is from birth to age 3. The most important predictor of a child’s educational success is the quality and quantity of adult-child interactions during these earliest years. The TMW Center, headed by Dr. Dana Suskind, is the leading organization in developing curriculum and research-based interventions to educate caregivers about the power of parent talk.
The product is a wearable device for children that can capture information about the quality + quantity of conversation they hear. The goal is to provide accurate, real-time feedback that empowers parents and caregivers to create the best language environment for their children.
The Senior Speech Processing Engineer will take ownership in making technical decisions that shape the future of our product and platform. This person will be the first engineering hire to join a team of experts in early childhood development, and will also have a strong voice in defining longer-term strategy. This is a full-time position. Compensation is competitive and commensurate with experience.
- Translate the expertise of the childhood development researchers into real-world products
- Implement and evaluate algorithms to detect and categorize adult + child speech
- Work with large raw audio datasets to develop novel models
- Define feature specifications to assist in prototype creation for wearable device
Skills & requirements
Knowledge, Skills, and Abilities
- Experience with digital signal processing for audio and/or speech
- Ability to write production-level code and work with large, unstructured audio datasets
Additional nice-to-have capabilities include:
- Experience with speaker diarization, automatic speech recognition, speaker verification
- Experience with machine learning techniques and model evaluation metrics
- Experience with wearables or ultra low power / ultra small footprint software design
- 3+ years work experience in engineering
- Be able to work in Chicago, NYC, or remotely