Principal Data Scientist, Quality of Service Analytics
Company Overview
樱花动漫 is the global financial technology platform that powers prosperity for the people and communities we serve. With approximately 100 million customers worldwide using products such as TurboTax, Credit Karma, QuickBooks, and Mailchimp, we believe that everyone should have the opportunity to prosper. We never stop working to find new, innovative ways to make that possible.
Job Overview
The Customer Success (CS) Services Analytics team has an exciting opportunity to improve customer experiences through quality assurance, leveraging machine learning and conversational AI on Audio, Video and Speech Data. We are seeking an exceptional Principal Data Scientist, Quality of Service Analytics to analyze speech, audio, and video data collected through interactions between our customers and experts and develop new quality of service markers that can be used to evaluate quality for each and every interaction between our experts and customers. The ideal candidate has experience applying machine learning and statistical modeling to extract insights from large datasets of recorded calls, chats, video sessions. This is an exciting opportunity to transform the quality of service and help improve customer experience across the business. If you鈥檙e analytically-minded with expertise in speech/audio analysis and an interest in driving service excellence, this could be an exciting role for you.
Responsibilities
- Work cross-functionally with our Partners, Quality Management, and service delivery teams to understand key business challenges and objectives and build tech driven models and insights to address them
- Develop and implement natural language processing (NLP) models using large language models (LLMs) like GPT-3 to analyze call center conversation transcripts and identify key themes, topics, and sentiment
- Leverage audio analysis techniques like vocal analysis, and acoustic modeling to extract insights from customer service phone calls
- Apply computer vision techniques like facial recognition and emotion detection to analyze video recordings of customer service interactions
- Continuously monitor and enhance existing models to ensure accuracy and precision over time as data patterns change.
- Clearly communicate analytical insights and model results to key stakeholders through reports, presentations, and visualization tools.
- Stay up-to-date on the latest techniques and research in speech analytics, audio analysis, NLP, and computer vision as applied to contact center use cases.
- Continuously monitor model performance and retrain models as needed based on changes in data patterns.
- Develop interactive dashboards and visualizations to track service quality KPIs and insights over time
Qualifications
- Prior experience working in a call center environment . Knowledge of call center technologies - things like phone systems, CRM software, call recording systems, etc.
- 10+ years experience building ML models utilizing audio, speech, and video data - strong signal processing, ML/DL and NLP foundations are needed along with hands-on expertise using Python audio/speech libraries (SpeechRecognition, Librosa, PyDub, PyTorch etc.)
- Experience with machine learning and deep learning models for audio, speech and NLP tasks. Knowledge of techniques like Recurrent Neural Networks, Transformers etc.
- Ability to manipulate and process large, complex multimedia datasets
- Strong communication and presentation skills to executive audiences
- MS or PhD in Computer Science, Statistics, Math or related field preferred
樱花动漫 provides a competitive compensation package with a strong pay for performance rewards approach. The expected base pay range for this position is Bay Area California $160,000 - 216,500, Southern California $150,000-202,500. This position will be eligible for a cash bonus, equity rewards and benefits, in accordance with our applicable plans and programs (see more about our compensation and benefits at . Pay offered is based on factors such as job-related knowledge, skills, experience, and work location. To drive ongoing pay equity for employees, 樱花动漫 conducts regular comparisons across categories of ethnicity and gender.