AI Engineer

We are looking for an AI Engineer based in Latin America to work on a long-term project for one of our clients, a Data Analytics and Business Intelligence services company based in Los Angeles, California.

The person in this role will work as an AI Engineer to design and build AI-powered products that improve how the heavy equipment industry accesses service knowledge and parts information, leading the development of intelligent retrieval systems, agentic architectures, and AI solutions that capture field repairs and generate verified training content while balancing advanced AI techniques with production reliability.

Responsibilities

• Design and implement intelligent retrieval systems that help technicians quickly find procedures, parts, and troubleshooting guidance across multiple service data sources.
• Build and maintain RAG pipelines, graph-based retrieval approaches, and agentic architectures to answer complex diagnostic questions across structured and unstructured data.
• Develop pipelines that transform real-world service knowledge into verified AI training content, including multimodal extraction and content synthesis systems.
• Design validation workflows, confidence scoring systems, and feedback loops to ground AI output in actual repair outcomes and continuously improve accuracy.
• Architect and deploy production-grade AI systems in cloud environments (GCP and AWS), integrating advanced AI models with proprietary data and scaling retrieval workloads reliably.
• Design APIs and controlled data access patterns that enable customers to build AI solutions using proprietary data while managing hallucination risk and enforcing scope controls.
• Collaborate cross-functionally with product, engineering, and customer success teams to translate user needs into scalable AI capabilities.
• Ensure AI systems meet high standards for reliability, scalability, security, and cost efficiency in production environments.

Requirements

• Advanced Level of English
• 5+ years of experience working as a software engineer.
• 2+ years of experience building production AI or machine learning systems, including retrieval-based architectures such as RAG pipelines, agentic systems, or tool-calling workflows.
• 5+ years of professional experience with Python and building production-grade systems using clean architecture and engineering best practices.
• 2+ years of experience deploying and scaling AI workloads on cloud platforms such as GCP or AWS.
• Strong understanding of embedding strategies, vector databases, and retrieval techniques, including single-step retrieval, multi-step reasoning, and graph-based retrieval approaches (GraphRAG or knowledge graphs preferred).
• Hands-on experience working with LLM APIs (e.g., OpenAI, Anthropic, Gemini), prompt engineering, and multimodal models processing text, images, video, and documents.
• Demonstrated ability to design and evaluate high-accuracy AI systems, including retrieval quality measurement, validation strategies, and graceful failure mechanisms.
• Strong product mindset, with the ability to translate technical capabilities into user value and collaborate effectively with product managers and cross-functional teams.
• Learning agility and the ability to stay current with emerging AI technologies, quickly evaluate new tools and techniques, and distinguish meaningful advances from hype.

Bonus Points

• Bachelor’s Degree in Computer Science, Systems Engineering or related fields

What we offer

• Long term positions.
• Compensation in USD.
• Paid time off.
• Cool clients and products.
• Work with great engineers.

4tech