AI Engineer

Summary

Join a newly formed AI product development team at RYZ Labs to build intelligent systems using proprietary business data. This hands-on role focuses on experimentation, rapid prototyping, and full-lifecycle product implementation. You will collaborate with various stakeholders to deliver high-value tools generating reports and analysis in multiple formats. The team leverages LLMs, RAG, and cloud-native infrastructure to deliver business insights. The ideal candidate will have experience in backend or platform development, proficiency in Python, and a strong foundation in cloud computing. This is a remote position with a focus on autonomy, learning, and growth within a startup environment.

Requirements

• 3+ years of experience in software engineering, preferably in backend or platform development roles
• Proficiency in Python, including experience with data manipulation, APIs, and automation
• Strong foundation in cloud computing, with proven experience in AWS and/or Google Cloud Platform (GCP) services (e.g., Lambda, S3, Cloud Functions, and Vertex AI)
• Experience with version control (Git), CI/CD pipelines, and containerization (Docker)

Responsibilities

• Design, build, and deploy AI-powered products using proprietary structured and unstructured business data
• Implement RAG systems and AI agents leveraging foundation models to handle client queries and target discovery
• Integrate AI pipelines with external tools for web search, information access, and document generation
• Collaborate with cross-functional teams to define and implement cloud-native architectures using AWS and/or GCP
• Prototype and experiment with LLM-based workflows (e.g., prompt engineering, tool usage, agentic orchestration)
• Ensure scalability, performance, and security in cloud-hosted environments
• Contribute to the AI product roadmap and provide technical guidance on implementation strategies

Preferred Qualifications

• Familiarity with LLMs (e.g., OpenAI, Anthropic, Claude, and Mistral) and understanding of transformer-based models
• Hands-on experience building or experimenting with Retrieval-Augmented Generation (RAG) systems or agentic frameworks (e.g., LangChain, LlamaIndex)
• Ability to integrate third-party tools/APIs for document generation and workflow automation
• Knowledge of vector databases (e.g., Pinecone, Weaviate, FAISS) and semantic search
• Demonstrated ability to work with unstructured data and knowledge graphs
• Demonstrated interest or side projects in AI, NLP, or machine learning

Benefits

Our teams are remote and distributed throughout the US and Latam