AI Engineer

Role Profile

Build the AI Data Backbone: Write scripts to extract, clean, and chunk structured/unstructured data from our central Lakehouse to feature store and RAG systems

Production Prompt Engineering: Design, test, and version-control prompts, system instructions, and JSON tool-calling schemas for different LLM providers

Own Automated Evals: Build repeatable evaluation pipelines for classical ML and LLMs

Deployment & automation: Package AI features and data workflows using GIT, Jenkins or any equivalent tool

Competencies & Qualifications

Core Software Discipline: Write clean, modular, asynchronous Python; write complex SQL queries; practice strict Git and CI/CD version control.

Data Engineering (ETL/Spark): Hands-on ability to build retry-able ETL/ELT pipelines and write efficient PySpark jobs to process large training/evaluation datasets.

Applied AI & RAG: Deep understanding of vector embeddings, semantic search, vector and AI orchestration frameworks .

AI Quality Assurance: Experience with model evaluation tools and methodologies

Infrastructure comfortable with basic Linux admin& bash commands, monitoring and automate Ai services.

Desired Candidate Profile

Core Software Discipline: Write clean, modular, asynchronous Python ; write complex SQL queries; practice strict Git and CI/CD version control. Data Engineering (ETL/Spark): Hands-on ability to build retry-able ETL/ELT pipelines and write efficient PySpark jobs to process large training/evaluation datasets. Applied AI & RAG: Deep understanding of vector embeddings, semantic search, vector and AI orchestration frameworks . AI Quality Assurance: Experience with model evaluation tools and methodologies Infrastructure comfortable with basic Linux admin& bash commands, monitoring and automate Ai services.