Data Scientist / AI Engineer (Generative AI, GCP)

Quick Facts

• Role: Data Scientist / AI Engineer focused on Generative AI for customer conversation analytics

• Tech stack: Google Cloud (Speech-to-Text, Gemini, Vertex AI, BigQuery)

Description

You will build and deploy end-to-end analytics pipelines that turn customer conversation audio and transcripts into insights for business decision-making. The solutions will support sentiment analysis, discovery of recurring topics, and improvements to consultant workflows using Google Cloud AI/ML services. You will combine data science expertise with practical Generative AI experience, plus strong data analysis and visualization skills.

Responsibilities

• Design and implement pipelines for extracting and processing large volumes of conversation data using APIs and Cloud Storage

• Use topic modeling and configurable information extraction to identify recurring customer problems and business-relevant trends

• Develop and refine analytical and predictive models for conversation sentiment, query metrics, and solution effectiveness

• Configure analytics dashboards and export conversation data to BigQuery for advanced SQL analysis

• Create dashboards presenting key performance indicators

• Implement production API integrations, including request limit management, retry logic with increasing intervals, and latency control

• Use Cloud DLP API to remove or mask data that could identify people in transcripts and audio files

• Collect client requirements and define schedules for AI pilot projects

• Explain LLM and AI solution topics to non-technical stakeholders

Requirements

• Very good knowledge of Python and SQL for data processing, automation, and advanced analytics on large datasets

• Ability to write complex BigQuery SQL queries, including JOIN, window functions, and aggregations

• Experience using Python libraries to transform/analyze data and derive business conclusions

• Experience implementing RAG and managing vector databases or indexes (e.g., pgvector in Cloud SQL or Vertex Vector Search)

• Ability to define and monitor AI evaluation metrics (e.g., hallucination frequency, prediction latency) and assess responsible-AI filter performance

• Strong foundation in statistical analysis, including trend analysis on datasets with millions of records and forecasting service-usage growth

• Ability to visualize data and present analytics results in a business-usable way

• Ability to explain LLM concepts to non-technical people, including pre-training vs fine-tuning and LLM vs traditional ML

• Experience delivering projects for strategic clients: requirements gathering and AI pilot planning

Benefits

• B2B collaboration

• Contribute to the development of AI solutions supporting customer experience analytics

• Work across the full workflow: data processing, modeling, visualization, and production deployment

• Direct collaboration with clients to define requirements and implement AI pilot projects