Business Intelligence Engineer- Ii, Sales AI

Amazon Amazon · Big Tech · IN, KA, Bengaluru · Business Intelligence

This role is for a Business Intelligence Engineer focused on building the data foundations and pipelines for AI agents in the advertising and B2B sales domain. The engineer will design data models, create analytical infrastructure, and ensure data flows from various systems into a unified context layer for AI agents to reason over. They will also build reporting and measurement systems to track agent performance and business impact. The role involves end-to-end ownership of data, from ingestion to serving layers, and collaboration with Applied Scientists.

What you'd actually do

  1. Design and build data pipelines that ingest, transform, and serve advertiser context from dozens of source systems (campaign data, deal history, behavioral signals, conversation transcripts, account metadata).
  2. Create and maintain data models that unify fragmented advertiser information into a coherent, queryable representation for AI agents.
  3. Build the measurement and reporting infrastructure that tracks agent performance, context quality, and business impact (adoption, accuracy, revenue influence).
  4. Partner with software engineers to design data serving layers optimized for low-latency agent retrieval.
  5. Conduct deep data analysis to identify coverage gaps, quality issues, and opportunities to enrich advertiser context.

Skills

Required

  • data modeling
  • data warehousing
  • ETL pipelines
  • SQL
  • large-scale data warehousing (Redshift, Spark, or equivalent)

Nice to have

  • data mining
  • ETL
  • databases in a business environment with large-scale, complex datasets
  • scripting for automation (e.g., Python, Perl, Ruby)
  • building large-scale machine learning models and infrastructure for online recommendation, ads ranking, personalization, or search
  • AWS services including S3, Redshift, Sagemaker, EMR, Kinesis, Lambda, and EC2
  • real-time or near-real-time data serving patterns (streaming, change data capture, materialized views)
  • Generative AI data requirements — embeddings, vector stores, or context preparation for LLMs

What the JD emphasized

  • AI agents
  • advertiser context
  • data foundations
  • context layer
  • agent performance
  • business impact
  • data pipelines
  • AI agents
  • data modeling
  • integrated
  • served
  • agent retrieval
  • data analysis
  • coverage gaps
  • quality issues
  • enrich advertiser context
  • data quality standards
  • validation
  • monitoring
  • alerting
  • production data pipelines
  • Applied Scientists
  • feature engineering
  • data preparation
  • machine learning models

Other signals

  • AI agents
  • data foundations
  • contextual backbone
  • data pipelines
  • analytical infrastructure