Principal Backend Engineer & AI (Node.js + Java)

We are looking for a Senior Software Engineer specializing in Node.js, Java, and AI integration to join our engineering team. In this role, you’ll play a key part in designing, developing, and maintaining high-performance backend services that power our enterprise applications. You’ll collaborate closely with cross-functional teams to ensure scalable, reliable, and secure solutions are delivered.

Location: Mexico (Remote)

Qualifications we are looking for:

• Multi-Stack Backend Engineering: Lead the design and development of scalable microservices using Node.js and Spring Boot (Java), ensuring high performance and architectural consistency across different backend environments.
• AI/LLM Architecture & Integration: Architect and implement hands-on integrations with LLM APIs (OpenAI, Anthropic, etc.), focusing on production-grade reliability and seamless connection with existing backend services.
• Advanced RAG & Orchestration: Design and deploy Retrieval-Augmented Generation (RAG) patterns and AI orchestration workflows to empower applications with proprietary data context and intelligent decision-making.
• Asynchronous Systems Design: Leverage deep experience in Message Queues (MQ) to build resilient, event-driven architectures that manage the latency and throughput requirements of AI/ML workloads.
• Vector Data Strategy: Implement and manage vector databases (e.g., Pinecone, Milvus) and embedding strategies to support semantic search and efficient long-term memory for AI agents.
• Infrastructure & Automation Leadership: Drive the adoption of Infrastructure as Code (IaC) using Terraform and manage sophisticated CI/CD pipelines (GitHub, JFrog Artifactory) to automate the deployment of complex AI-enabled services.
• AI-Driven API Development: Design and standardize AI-powered API endpoints, ensuring they are secure, cost-optimized, and capable of handling complex model orchestrations.
• Technical Mentorship & Governance: Provide expert guidance to engineering teams on Prompt Engineering best practices, clean code in both Node.js and Java, and the ethical/secure integration of AI technologies.
• Performance & Observability: Monitor and optimize system performance, focusing on LLM response times, token efficiency, and infrastructure costs within cloud environments (GCP/Azure).

Requirements:

• 5–8 years of professional software development experience.
• Node.js and Spring Boot (Expert).
• Experience with Java (Advanced).
• Experience with tools - Github, Terraform , JFrog Artifactory.
• Deep experience with MQ (Message Queue).
• Hands-on experience integrating AI/ML capabilities into backend architectures.
• Hands-on experience with LLM APIs, Prompt Engineering, or RAG (Retrieval-Augmented Generation).
• Experience implementing AI orchestration, vector databases, or AI-driven API endpoints.
• Experience with LLM integration (e.g., OpenAI API, Anthropic, or local models).

Nice to have:

• Experience with Cloud services in GCP like Dataflow, Big Query, Azure Services- at a minimum EventHub.
• Python (specifically for AI/Data processing scripts)