AI Data Engineer - Senior Consultant

AI Data Engineer Senior Consultant responsible for building and operating data, features, and GenAI foundations for Human Capital AI products. This role involves designing, building, and running the data and retrieval layer for AI/ML and GenAI solutions, including LLM-enabled capabilities, RAG patterns, governed datasets, feature engineering, and implementing safety/privacy controls. The role also contributes to MLOps/LLMOps and production operations.

What you'd actually do

  1. Design, build, and run the trusted, governed data + feature + retrieval layer used by AI/ML and GenAI solutions.
  2. Build and operationalize LLM-enabled capabilities (e.g., copilots, HR knowledge assistants, summarization, policy Q&A) using Claude/GPT(Codex)/Gemini, including secure endpoints, tool/function calling, and reusable prompt/context patterns.
  3. Implement LLM application patterns including RAG, document ingestion/chunking, embeddings, vector/hybrid search, and retrieval/evaluation telemetry.
  4. Deliver governed datasets and feature engineering/serving for ML training and real-time inference (online/offline consistency, caching, latency SLOs, backfills).
  5. Implement safety, privacy, and access controls (PII handling, prompt-injection defenses, content filtering, policy-based access) with security and risk stakeholders.

Skills

Required

  • Building and delivering LLM/GenAI solutions
  • Prompt/context design
  • Tool/function calling
  • Evaluation
  • Production integration
  • RAG/retrieval implementation
  • Document processing
  • Embeddings
  • Vector/hybrid search
  • Enterprise governance controls
  • Modern data & AI engineering
  • Data modeling
  • Batch/streaming pipelines
  • Structured/unstructured data processing
  • Feature engineering/serving
  • Building production, real-time inference services
  • API design

What the JD emphasized

  • 4+ years building and delivering LLM/GenAI solutions with Claude/GPT(Codex)/Gemini-class models, including prompt/context design, tool/function calling, evaluation, and production integration.
  • 4+ years implementing RAG/retrieval (document processing, embeddings, vector/hybrid search) with enterprise governance controls.
  • 4+ years of modern data & AI engineering, including data modeling, batch/streaming pipelines, structured/unstructured processing, and feature engineering/serving fundamentals.
  • 4+ years building production, real-time inference services (API design, late

Other signals

  • LLM application patterns
  • RAG
  • vector search
  • feature engineering
  • real-time inference
  • production pipelines