AI Engineer

Jobtailor; Belo Horizonte; Presencial; BRL 180 000 - 280 000; Tempo integral

Resumo da oferta

Jobtailor in Belo Horizonte, Brazil seeks a skilled AI engineer to develop and deploy Generative AI systems, design robust RAG architectures, and integrate models with enterprise platforms.

You will optimize prompts, test fine-tuning approaches, and ensure governance and cost efficiency of LLM calls, collaborating with cross-functional teams.

Qualificações

• Strong proficiency in Python for software and AI development.
• Experience with generative AI orchestrators and frameworks: LangChain, LlamaIndex, or LangGraph.
• Familiarity with consuming APIs from LLM providers (OpenAI, Anthropic, Google Vertex AI).
• Hands-on experience with vector databases (ChromaDB, Pinecone, Qdrant, pgvector, etc.).
• Knowledge of software engineering best practices (Git, Docker, RESTful APIs/gRPC) applied to AI (basic MLOps).

Responsabilidades

• Develop and deploy Generative AI systems and autonomous agents.
• Design and optimize RAG architectures using vector databases.
• Develop and test prompt engineering, few-shot prompting, and fine-tuning strategies for foundation models.
• Collaborate on building connectors and APIs to integrate AI models with enterprise systems.
• Ensure governance, security, reduction of hallucinations, and cost optimization for LLM API calls.

Conhecimentos

AI development

Prompt engineering

MLOps basics

Software engineering

Ferramentas

Python

LangChain

LlamaIndex

LangGraph

OpenAI API

ChromaDB

Pinecone

Qdrant

Docker

RESTful APIs

gRPC

Git

Descrição da oferta de emprego

Responsibilities

• Develop and deploy Generative Artificial Intelligence systems and multi-agent AI agents (stateful and autonomous).
• Design and optimize RAG (Retrieval-Augmented Generation) architectures using vector databases to build intelligent knowledge bases.
• Develop and test advanced prompt engineering strategies, few‑shot prompting techniques, and fine‑tuning approaches for foundation models.
• Collaborate on building robust connectors and APIs to integrate AI models with enterprise systems such as CRMs, ERPs, and e‑commerce platforms.
• Ensure governance, security, reduction of hallucinations, and cost optimization for LLM API calls.

Requirements

• Strong proficiency in Python for software and AI development.
• Experience with generative AI orchestrators and frameworks: LangChain, LlamaIndex, or LangGraph.
• Familiarity with consuming APIs from LLM providers (OpenAI, Anthropic, Google Vertex AI).
• Hands‑on experience with vector databases (ChromaDB, Pinecone, Qdrant, pgvector, etc.).
• Knowledge of software engineering best practices (Git, Docker, RESTful APIs/gRPC) applied to AI (basic MLOps).

Core Competencies

Demonstrates expertise in developing and deploying Generative Artificial Intelligence systems, with a strong focus on prompt engineering, RAG architectures, and integration with enterprise systems. Proficient in Python and familiar with best practices in software engineering and MLOps.