1061- AI/RAG Engineer

Location: Remote

Department: Information Technology

We need an English-fluent AI/RAG Engineer, based in Latin America, available to work remotely.

We are looking for someone with exceptional communication and relationship-building skills, who embraces changes while maintaining strong attention to detail. An interested and proactive person, whos constantly learning and improving their skills.

Are you the one we are looking for?

Responsibilities:

• Architect and implement scalable AI integration patterns (RAG pipelines, agentic workflows, MCP tools, structured extraction, summarization, compliance intelligence) that can be reused across the platform
• Design and deliver production-grade AI-powered features embedded within mission-critical procurement workflows, including internal tooling
• Define and implement evaluation frameworks, observability, and guardrails to ensure model quality, cost governance, security, and compliance
• Partner with architecture leadership to evolve our legacy monolithic platform toward more modular, service-oriented capabilities
• Establish engineering standards for AI systems, including testing strategies, prompt/version management, model lifecycle practices, and performance monitoring
• Collaborate cross-functionally with Product, UX and domain subject matter experts (internal and external) to ensure AI solutions solve real user problems
• Contribute to architectural reviews and technical design sessions to ensure alignment with long-term platform modernization goals
• Use PlanetBids issued AI tools and platforms to seek efficiencies in your role
• Produce clear technical documentation to support maintainability and knowledge sharing.

Requirements:

• 3–5 years of software engineering experience, with exposure to AI/LLM-based solutions
• Hands-on experience with LLM integrations (e.g., RAG, prompt engineering, summarization, or structured data extraction)
• Proficiency in Python, Node.js, or similar, with experience building APIs and scalable services
• Experience with cloud platforms (AWS, GCP, or Azure)
• Familiarity with vector databases or retrieval systems (e.g., Pinecone, FAISS, etc.)
• Solid understanding of modular or service-oriented architectures
• Experience with monitoring, logging, and system performance in production environments
• Ability to collaborate with cross-functional teams and translate business needs into technical solutions.