Generative AI Engineer for Data Systems

Generative AI Engineer for Data Systems

Transforming data workflows through agentic AI, conversational interfaces, and AI-assisted analytics

Position Overview
We are seeking a Generative AI Engineer for Data Systems to lead the design and integration of AI-first tooling for modern data workflows. This role focuses on building AI-powered services such as information extraction pipelines, smart questionnaires, AI pair-programming assistants, and natural language interfaces to democratize access to data and accelerate productivity across statistical, engineering, and analytical teams.

Key Responsibilities

GenAI-Enabled Data Workflows

• Design and deploy AI agents that automate steps in data pipelines (e.g., transformation, validation, documentation)
• Develop workflows that combine LLMs with data tools (SQL engines, ETL jobs, metadata catalogs)
• Integrate agentic AI frameworks into notebooks, dashboards, and API layers
• Build systems where LLMs assist in tasks such as table joining, schema inference, or chart creation

Smart Forms & Adaptive Questionnaires

• Implement smart, AI-assisted questionnaires that adapt based on user input or metadata
• Build NLP-powered survey tools that recommend questions, auto-fill responses, or extract structured data from free text
• Enhance survey response validation and quality using LLM-based reasoning and logic

AI Pair-Programming for Data Practitioners

• Integrate AI coding copilots into environments used by statisticians, data scientists, and engineers
• Provide context-aware code generation, auto-documentation, and test creation inside IDEs (RStudio, VSCode, Jupyter)
• Build internal copilots for tasks such as model diagnostics, pipeline debugging, or script refactoring
• Collaborate with users to understand pain points and optimize prompt engineering strategies

Natural Language & Conversational Interfaces

• Develop conversational data tools that allow users to ask questions and get answers directly from structured and unstructured datasets
• Embed GenAI-powered search and exploration into data catalogs, dashboards, and web interfaces
• Fine-tune or prompt-engineer LLMs for safe, accurate, and explainable answers in data contexts
• Integrate multi-modal interfaces where users can speak, type, or upload to interact with datasets

Required Qualifications

Technical Skills

• 6+ years working at the intersection of data engineering, machine learning, or AI tooling
• Hands-on experience with LLMs and frameworks like LangChain, Haystack, OpenAI, or Transformers
• Proficiency in Python and experience working with data tools (SQL, pandas, dbt, Apache Airflow)
• Familiarity with frontend or UI libraries for chatbot-like or form-based applications (Streamlit, Gradio, Shiny)

AI/ML Engineering

• Experience integrating or fine-tuning LLMs for structured data tasks or decision support
• Understanding of prompt engineering, retrieval-augmented generation (RAG), and embedding techniques
• Comfort working with cloud APIs (OpenAI, Cohere, Anthropic) and vector databases (FAISS, Weaviate, Chroma)
• Ability to build secure, governed systems for LLM deployment in enterprise settings

Preferred Qualifications

• Degree in Computer Science, Data Science, Statistics, or a related field
• Experience working with or supporting data scientists and statisticians