Inteligencia Artificial jobs in Brazil

AI Engineer (Search Engine)

Insight Global's Client

10 month extending contract

Shared upon initial WhatsApp screening call

Fully Remote

10AM - 6PM BRT (9AM-5PM EST)

Immediate interviews available — 2 rounds can close by end of next week.

• Build backend features for an existing Retrieval-Augmented Generation (RAG) service.
• Work on semantic chunking strategies, improve automated evaluation pipeline, and fine-tune LLMs for textual RAG use cases.
• Collaborate with DevOps for production rollout; deployments to non-prod environments.
• Hands-on experimentation, model development, and backend engineering; strong communication and collaboration with the team.

• Ability to work full-time hours on a contract basis (10AM - 6PM BRT)
• Strong communication skills
• CLT ONLY (This cannot change to PJ)
• No health benefits provided in CLT benefits
• Needs to be able to start within 2-3 weeks
• Paid on a monthly basis, no overtime

• 1+ years of experience as a Search Engineer or AI Engineer
• Search Technology Experience – OpenSearch, building scalable search systems
• 2+ years of Python development experience, including API creation, model training, testing, and general backend programming
• Familiarity with LangChain for building LLM workflows using tools, memory, and retrieval
• Strong communication skills – able to work independently while providing clear updates to the team

• Familiarity with AWS infrastructure (IAM, VPC, S3, etc.)
• Exposure to RAG architectures, specifically textual RAG use cases

We are hiring one AI / LLM Engineer (1 Mid-Level) to join a small, focused team building backend features for an existing Retrieval-Augmented Generation (RAG) service. Your primary focus will be building and optimizing RAG models for search across large-scale medical and scientific documents, including pre-processing and embedding over half a billion documents to ensure they are searchable and contextually accurate. You’ll work on semantic chunking strategies, improving the automated evaluation pipeline, and fine-tuning LLMs for textual RAG use cases. The role involves hands-on experimentation, model development, and backend engineering, with deployments to non-prod environments and collaboration with DevOps for production rollout. While this is a heads-down, individual contributor role, strong communication and collaboration with the team are essential.