Data Scientist / AI Engineer (Generative AI, GCP)

Quick Facts

• Role: Data Scientist / AI Engineer focused on Generative AI and Google Cloud

• Primary goal: Turn customer conversation audio + transcripts into insights that support business decisions and consulting effectiveness

Description

You will design and implement end-to-end analytics pipelines that ingest and process large volumes of conversational data using Google Cloud AI services (Speech-to-Text, Gemini, Vertex AI). The solutions will support topic discovery, customer sentiment analysis, recurring-issue identification, and improved consulting workflows through dashboards and production-ready APIs.

Responsibilities

• Design and deploy data ingestion and processing pipelines for customer conversation recordings and transcripts using APIs and Cloud Storage

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

• Develop and improve analytical and predictive models for sentiment, query metrics, and the effectiveness of solutions supporting consultants

• Export conversation data to BigQuery and build analytics dashboards for key performance indicators (KPIs)

• Build production API integrations with query-limit management, backoff with increasing time intervals for retries, and latency control

• Implement data removal or masking to protect personally identifiable information in transcripts and audio using Cloud DLP API

• Gather client requirements and define timelines for AI pilot projects

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

Requirements

• Very strong Python and SQL for data processing, automation, and advanced analysis of large datasets

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

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

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

• Ability to define and monitor AI evaluation metrics such as hallucination frequency and prediction latency, plus responsible-AI filter effectiveness

• Strong statistical fundamentals for trend analysis on million-row datasets and forecasting

• Strong ability to visualize data and present analysis results in a business-friendly way

• Ability to explain LLM-related topics to non-technical audiences (pre-training vs fine-tuning; LLM vs traditional ML)

• Experience running projects for strategic clients, including requirements gathering and planning AI pilots

Benefits

• B2B collaboration model

• Opportunity to develop AI solutions supporting customer experience analytics

• Direct client collaboration to define requirements and deliver AI pilot projects

• Work end-to-end with Google Cloud technologies (processing, modeling, visualization, and production deployment)