Backend Node.js Engineer - AI/LLM Integration

job summary:

We are seeking a Back End Node.js Engineer with hands-on AI implementation experience to build scalable backend services and AI-enabled capabilities for enterprise applications. This role focuses on designing production-ready APIs, microservices, and backend orchestration layers that integrate with LLMs, RAG pipelines, vector search, caching, and enterprise data sources.

The ideal candidate is a strong backend engineer with deep experience in Node.js, TypeScript, REST APIs, microservices, Redis/caching, cloud deployments, CI/CD, and production support, with proven experience building AI-powered systems using LLM APIs, embeddings, vector databases, RAG, prompt orchestration, tool calling, and response validation.

This is not a front-end-focused role and not a pure data science or ML research role. Candidates should be able to clearly explain backend architecture, AI integration design, production tradeoffs, and how they have built reliable AI-enabled services in a real application environment.

location: Sunnyvale, California

job type: Contract

salary: $65 - 70 per hour

work hours: 9am to 5pm

education: Bachelors



responsibilities:

• Design, build, and maintain scalable Node.js/TypeScript backend services, REST APIs, microservices, and backend orchestration layers.
• Develop AI-enabled backend services that integrate with LLM APIs, RAG workflows, embeddings, vector databases, and enterprise knowledge sources.
• Build backend systems that support intelligent search, document retrieval, summarization, recommendations, workflow automation, or agent-assist capabilities.
• Design and implement prompt orchestration, conversation context management, tool/function calling, and structured response handling.
• Integrate backend services with databases, caches, messaging systems, and cloud-native infrastructure.
• Implement Redis/caching strategies, rate limiting, session/context handling, retries, timeouts, and API performance optimization.
• Design secure APIs with proper authentication, authorization, validation, error handling, logging, and monitoring.
• Support asynchronous and event-driven processing using tools such as Kafka, queues, or background workers.
• Build and maintain CI/CD pipelines, automated testing, and production deployment processes.
• Monitor backend and AI system performance, including latency, errors, token usage, cost, retrieval quality, and system reliability.
• Troubleshoot production issues and improve the scalability, reliability, and accuracy of AI-enabled backend services.
• Collaborate with product, architecture, front-end, data, and platform teams to deliver secure, production-ready AI capabilities.

qualifications:

Strong hands-on experience with Node.js, TypeScript, Express.js and/or NestJS.

Experience building REST APIs, microservices, backend orchestration layers, and distributed systems.

Hands-on experience integrating LLMs into backend applications using OpenAI, Azure OpenAI, Claude, Gemini, AWS Bedrock, or similar.

Experience with RAG, embeddings, vector search/vector databases, prompt engineering, AI agents, tool/function calling, and response validation.

Strong backend fundamentals: API contracts, authentication/authorization, error handling, logging, retries, rate limiting, timeouts, and performance tuning.

Experience with Redis/caching, including TTLs, cache invalidation, session/context storage, or rate limiting.

Experience with PostgreSQL, MongoDB, MySQL, or similar databases.

Experience with AWS/Azure/Google Cloud Platform, Docker, Kubernetes, CI/CD, Jenkins, GitHub Actions, or similar DevOps tools.

Experience with Kafka, RabbitMQ, SQS, background workers, or event-driven architecture.

Ability to explain AI design tradeoffs around latency, cost, accuracy, hallucination control, caching, security, and reliability.

Experience building AI-enabled features such as chatbots, agent-assist tools, document intelligence, semantic search, workflow automation, recommendations, or intelligent Q&A systems.

Equal Opportunity Employer: Race, Color, Religion, Sex, Sexual Orientation, Gender Identity, National Origin, Age, Genetic Information, Disability, Protected Veteran Status, or any other legally protected group status.

At Randstad Digital, we welcome people of all abilities and want to ensure that our hiring and interview process meets the needs of all applicants. If you require a reasonable accommodation to make your application or interview experience a great one, please contact

Pay offered to a successful candidate will be based on several factors including the candidate's education, work experience, work location, specific job duties, certifications, etc. In addition, Randstad Digital offers a comprehensive benefits package, including: medical, prescription, dental, vision, AD&D, and life insurance offerings, short-term disability, and a 401K plan (all benefits are based on eligibility).

This posting is open for thirty (30) days.


Qualified applicants in San Francisco with criminal histories will be considered for employment in accordance with the San Francisco Fair Chance Ordinance.



Qualified applicants with arrest or conviction records will be considered for employment in accordance with the Los Angeles County Fair Chance Ordinance for Employers and the California Fair Chance Act.



We will consider for employment all qualified Applicants, including those with criminal histories, in a manner consistent with the requirements of applicable state and local laws, including the City of Los Angeles' Fair Chance Initiative for Hiring Ordinance.