Job Description

About the Company

Our client is developing a next-generation conversational AI platform that aims to transform HR workflows. Based in Singapore and backed by strong financial support, they are building an enterprise-grade product featuring a 3D virtual human that functions as an intelligent HR partner. They are currently seeking a highly skilled and data-driven AI engineer to develop the intelligent core of their platform and architect the data pipelines that support it.

The Role

As the founding Generative AI Engineer, you will be responsible for both developing intelligent AI agents and building the data infrastructure that powers them. This hybrid role places you at the intersection of AI engineering and data architecture. You will work closely with the Lead Application Architect to ensure seamless integration between the data and application layers.

Key Responsibilities

AI Agent Development:

Design and build intelligent AI agents using frameworks such as LangChain or Semantic Kernel to automate complex HR workflows.

Data Pipeline Architecture:

Develop and maintain scalable data pipelines using tools like Azure Data Factory to ingest and process diverse data sources (e.g., third-party HRIS APIs, LinkedIn, user interactions).

RAG Implementation:

Design and optimize Retrieval-Augmented Generation (RAG) pipelines to connect LLMs with private company data stored in Azure AI Search.

Data Modeling & Transformation:

Structure and transform raw data within Azure Data Lake into clean, AI-ready datasets. Design schemas for both NoSQL (Azure Cosmos DB) and SQL (PostgreSQL) databases.

LLM Integration:

Implement state-of-the-art models from Azure OpenAI Service (e.g., GPT-4) to enable advanced conversational logic and reasoning.

Architectural Collaboration:

Work closely with the Lead Application Architect to align data architecture with application requirements.

Data Governance:

Ensure data quality, security, and compliance--particularly in alignment with regulations like GDPR.

Required Qualifications

Bachelor's or Master's degree in Computer Science, AI, Data Science, or a related field, or equivalent practical experience. 3-5 years of experience in data-centric software engineering roles (e.g., AI Engineer, Data Engineer, or Backend Engineer with a strong data focus). Proficient in Python and its data/AI ecosystem (e.g., Pandas, FastAPI). Experience designing and implementing data pipelines using tools like Azure Data Factory, Airflow, or similar. Hands-on experience with Large Language Models (e.g., OpenAI API) and frameworks like LangChain or Semantic Kernel. Strong data modeling skills and familiarity with both NoSQL and SQL databases. Proven ability to work on complex, collaborative engineering projects.

Preferred Qualifications (Nice-to-Haves)

Practical experience with the Azure Data & AI stack (ADF, Data Lake, Azure AI Search, Azure OpenAI). Experience deploying Retrieval-Augmented Generation systems in production. Knowledge of vector databases and embedding management. * Experience working in regulated environments (e.g., GDPR compliance).