About the Role
We are looking for a Sr. Data Analyst who can transform complex, non-numerical datasets into meaningful insights using a blend of data analytics and large language model (LLM) capabilities.
This role is ideal for someone who is passionate about analyzing text, audio, and video data, skilled at leveraging prompt engineering for deeper qualitative insights, and can bridge the gap between AI-driven analysis and business problem-solving.
Key Responsibilities
- Analyze and interpret unstructured datasets (text, audio, video) to identify key themes, trends, and opportunities for business and product improvement.
- Design, optimize, and apply prompt engineering techniques to extract, summarize, and classify information using Large Language Models (LLMs).
- Use NLP, speech-to-text, and computer vision tools for preprocessing and multi-modal data analysis.
- Develop and manage data taxonomies, tagging frameworks, and classification models for qualitative data.
- Collaborate with data engineers and product managers to build automated pipelines for unstructured data insights.
- Visualize and communicate findings clearly through dashboards, reports, and narrative summaries.
- Continuously explore advancements in AI-assisted data analytics and integrate relevant tools and frameworks into existing processes.
Requirements
- Bachelor's or Master's degree in Data Science, Computer Science, Computational Linguistics, or related field.
- Minimum experience 3 years with hands-on experience in unstructured data analytics (text, speech, or video).
- Proven proficiency in SQL.
- Proven proficiency in prompt engineering - ability to design structured prompts for LLMs to extract and analyze qualitative data effectively.
Strong working knowledge of Python is a must and knowledge of libraries such as pandas, numpy, NLTK, spaCy, or LangChain is a plus.
