Senior AI Engineer: LLMs, Azure OpenAI & APIs

Ernst & Young Advisory Services Sdn Bhd; Argentina; A distancia; ARS 135.820.000 - 271.641.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Global exposure

Continuous learning

Flexible work

Diversity & inclusion

Descripción de la vacante

Ernst & Young seeks a skilled AI/ML Engineer to design and implement AI-powered solutions using LLMs, RAG architectures, and prompt engineering. You will build Python-based services, APIs and automation components to scale AI applications, and integrate Azure OpenAI, Mistral and Qwen into enterprise-grade solutions.

Responsibilities include deploying serverless and containerized components with Azure Functions and Docker, developing ML models with Scikit-learn, TensorFlow and Keras, and

Formación

• Hands-on experience with LLMs, Azure OpenAI, RAG systems and prompt engineering.
• Experience with cloud-native development using Azure Functions and Azure storage/database services.
• Experience building REST APIs and working with GitHub, Docker and unit testing practices.

Responsabilidades

• Design, develop and implement AI/ML-powered solutions using LLMs, RAG architectures and prompt engineering best practices.
• Build Python-based services, APIs and automation components to support scalable AI applications.
• Integrate Azure OpenAI, Mistral, Qwen and other model providers into enterprise-grade solutions.
• Design and implement agentic AI workflows using frameworks such as Auto-Gen and LangGraph.
• Develop, train, validate and maintain machine learning/deep learning models using Scikit-learn, TensorFlow, Keras and N-BEATS where applicable.
• Integrate data storage and retrieval capabilities using Azure Blob Storage, CosmosDB, MongoDB/NoSQL concepts, and SQL.
• Deploy serverless and containerized components using Azure Functions, Docker and cloud-native engineering practices.
• Create unit tests, maintain code quality, use GitHub for version control, and support delivery through modern development tooling.
• Apply secure engineering practices including Linux server hardening and operational readiness considerations.
• Collaborate with distributed teams, communicate technical decisions clearly and contribute to reusable delivery assets.

Conocimientos

LLMs

Azure OpenAI

Mistral

Qwen

RAG Systems

Prompt Engineering

Agentic AI

N-BEATS

Scikit-learn

TensorFlow

Keras

Educación

Bachelor's or Master's degree

Herramientas

Python

Azure Blob Storage

CosmosDB

MongoDB

SQL

Azure Functions

Docker

GitHub

Unittest

VS Code

Linux Server Hardening

Descripción del empleo

Ernst & Young seeks a skilled AI/ML Engineer to design and implement AI-powered solutions using LLMs, RAG architectures, and prompt engineering. You will build Python-based services, APIs and automation components to scale AI applications, and integrate Azure OpenAI, Mistral and Qwen into enterprise-grade solutions.

Responsibilities include deploying serverless and containerized components with Azure Functions and Docker, developing ML models with Scikit-learn, TensorFlow and Keras, and