AI Engineer – Specialist

This is a fully remote position, open to applicants in Brazil.

📋 Description

• Develop and sustain AI solutions utilized in the product, encompassing RAG systems and integration with LLMs.

• Design and execute ingestion, embedding, and data retrieval pipelines (vector databases).

• Incorporate language models (OpenAI, Anthropic, open-source models, etc.) into product applications.

• Create and enhance prompts, chains, and agents tailored to specific business use cases.

• Assess performance, cost, and quality of models and AI pipelines (evaluations, accuracy/relevance metrics).

• Collaborate with backend teams to expose AI functionalities through APIs.

• Ensure scalability, security, and governance regarding data and model usage.

• Engage in code reviews and establish development standards for AI solutions.

• Keep the team updated on advancements and innovations within the generative AI landscape.

⛳️ Requirements

• Practical experience in developing AI solutions for production environments.

• In-depth understanding of RAG (Retrieval-Augmented Generation) and vector databases (Pinecone, Weaviate, pgvector, etc.).

• Proficient in integrating LLMs via API (OpenAI, Anthropic, etc.) and utilizing frameworks such as LangChain, LlamaIndex, or similar.

• Expertise in Python for the development of data and AI pipelines.

• Familiarity with prompt engineering methods and model evaluation techniques.

• Experience in consuming and creating secure REST/GraphQL APIs (OAuth 2.0, JWT).

• Knowledge of design patterns and SOLID principles as applied to AI systems.

• Experience in model fine-tuning and strategies for cost/latency optimization.

🏝️ Benefits

• AI observability tools (LangSmith, Langfuse, etc.)

• Integrations with cloud services (AWS, GCP, Azure)