Data Scientist

Key Responsibilities:

Conversation Analytics & Insight Generation

·       Design and implement analytics pipelines that extract meaningful patterns from large-scale chat conversation data

·       Develop facet extraction approaches using LLMs to categorize conversations by request type, task performed, and topic discussed

·       Build dashboards and reporting artifacts that communicate usage trends, emerging topics, and user behavior to stakeholders

·       Identify and quantify shifts in conversation patterns over time to inform product roadmap and content strategy

·       Translate analytical findings into actionable recommendations for platform improvement

Clustering & Unsupervised Learning

·       Architect and optimize hierarchical clustering pipelines using density-based algorithms (e.g., HDBSCAN) to group conversations by semantic similarity

·       Generate and manage text embeddings at scale using embedding models for downstream clustering and similarity tasks

·       Design multi-level clustering strategies that produce both granular groupings and higher-order category taxonomies

·       Evaluate cluster quality using persistence metrics, silhouette analysis, and domain-informed validation

·       Experiment with clustering parameters, distance metrics, and dimensionality reduction techniques to improve grouping coherence

Data Engineering & Pipeline Development

·       Build and maintain data pipelines using Python for ingesting, transforming, and analyzing conversation datasets

·       Develop automated workflows using cloud-native orchestration and compute services to run analytics at scale on scheduled cadences

·       Work with object storage, search engines, and relational databases to store and query analytical outputs

·       Implement caching, batching, and incremental processing strategies to handle large embedding and clustering workloads efficiently

·       Maintain reproducible analysis environments and version analytical artifacts (models, cluster outputs, embeddings)

LLM-Assisted Analysis

·       Design and refine LLM prompts for facet extraction, cluster labeling, and conversation summarization

·       Evaluate LLM output quality for analytical tasks and iterate on prompt strategies to improve accuracy

·       Leverage model infrastructure for embedding generation and LLM inference

·       Explore emerging techniques in LLM-driven data analysis, topic modeling, and automated insight generation

Quality & Testing

·       Develop evaluation frameworks to measure clustering quality, facet extraction accuracy, and analytical pipeline correctness

·       Build automated regression tests to detect drift in clustering outputs or degradation in categorization quality

·       Validate analytical results against known baselines and domain expertise

·       Document methodologies, assumptions, and limitations of analytical approaches

Security & Compliance

·       Assist with adherence to technology policies and comply with all security controls

·       Implement secure coding practices, particularly in handling personally identifiable information (PII) and sensitive data

·       Participate in threat modeling and security discussions for API and infrastructure components

·       Understand and apply organizational security standards and best practices