AI Engineer

Tractian; São Paulo; Híbrido; BRL 120.000 - 160.000; Tempo integral

Resumo da oferta

A leading technology firm in São Paulo is seeking an experienced LLM Applications Engineer. You will design, develop, and deploy production-ready applications leveraging large language models to enhance industrial operations. The ideal candidate has 1-4 years of relevant experience and a strong background in Python, REST API development, and LLM technologies. Join us to drive data-driven solutions and optimize prediction models.

Qualificações

• 1-4 years of experience in software engineering focused on backend development.
• Demonstrated experience building applications utilizing large language models.
• Strong proficiency in Python.

Responsabilidades

• Design and develop user-facing applications powered by large language models.
• Create and maintain high-performance APIs that integrate LLMs.
• Build intelligent document processing workflows using OCR technologies.

Conhecimentos

Python

REST API development

FastAPI

Flask

Django

Vector embeddings

Formação académica

Bachelor's degree in Computer Science or equivalent

Ferramentas

PostgreSQL

Redis

OpenAI

LangChain

LangGraph

Descrição da oferta de emprego

Data Science at TRACTIAN

The Data Science team at TRACTIAN focuses on extracting valuable insights from vast amounts of industrial data. Using advanced statistical methods, algorithms, and data visualization techniques, this team transforms raw data into actionable intelligence that drives decision-making across engineering, product development, and operational strategies. The team constantly works on optimizing prediction models, identifying trends, and providing data-driven solutions that directly enhance the company’s operational efficiency and the quality of its products.

What you'll do

We're seeking an experienced LLM Applications Engineer to design, develop, and deploy production-ready applications that harness the capabilities of large language models. In this role, you'll create robust APIs, implement intelligent information retrieval systems, and build resilient infrastructure that connects AI capabilities with real-world industrial applications.

Responsibilities

• Design and develop user-facing applications powered by large language models
• Create and maintain high-performance APIs that integrate LLMs with our platformImplement retrieval-augmented generation (RAG) systems for enhanced information access
• Build intelligent document processing workflows using OCR and LLM technologies
• Develop conversational interfaces that solve practical problems for our users
• Ensure system reliability with fallback mechanisms for provider outages
• Collaborate with product teams to define requirements and technical specifications

Requirements

• 1-4 years of experience in software engineering with a focus on backend development
• Bachelor's degree in Computer Science, Computer Engineering, Information Systems, or equivalent technical field
• Demonstrated experience building applications that utilize large language models
• Strong proficiency in Python and experience with web frameworks like FastAPI, Flask, or Django
• Experience designing, building, and maintaining production REST APIs
• Working knowledge of relational databases and SQL
• Familiarity with LLM orchestration tools such as LangChain or LangGraph
• Experience with vector embeddings and information retrieval systems
• History of shipping code to production environments

Preferred Qualifications

• Experience with LLM fine-tuning and model optimization techniques
• Knowledge of containerization and microservices architecture
• Experience with OCR and document processing technologies
• Understanding of performance optimization for AI applications

Technical Skills

• Programming: Python and/or Golang
• Frameworks: FastAPI, Flask, Django
• LLM Tools: LangChain, LangGraph
• API Development: REST, OpenAPI
• Databases: PostgreSQL, Redis, vector databases
• LLM Integration: OpenAI, Anthropic, and other providers
• Information Retrieval: Vector embeddings, semantic search
• Document Processing: OCR, PDF parsing