AI Backend Engineer

About Workerbee

Workerbee connects workers with employers through trusted introductions. By joining Workerbee you can be matched for project-based, contract, or permanent opportunities with leading organizations. Over time, Workerbee helps you:

• Keep a living record of what you have actually accomplished
• See how your experience carries across roles and paths
• Explore options without pressure to apply
• Move through change with clarity instead of urgency

About the Role

We are connected to those who hire talent and are in need of AI Backend Engineers. In this work, you will help employers solve complex problems and bring real value through hands-on expertise in backend services that carry AI models into production.

Responsibilities

• Build and maintain production services in Python, Go, or Node.js that expose models through versioned APIs with authentication, rate limiting, and usage metering
• Design retrieval and context pipelines that connect language models to customer data using vector stores, caching layers, and structured queries
• Stand up orchestration for multi-step agent and tool-calling workflows, including retries, timeouts, fallback routing, and idempotent job handling
• Instrument services for token cost, latency, and failure rates so product and finance teams can weigh output quality against spend
• Partner with data and platform teams on schema design, queue architecture, and event streaming that keep inference workloads stable under load

Requirements

• 5+ years building production backend systems with REST and event-driven APIs in AWS, Azure, or Google Cloud environments
• Hands-on work with LLM APIs, embeddings, and vector databases such as pgvector, Pinecone, or Weaviate, plus frameworks like LangChain or LlamaIndex
• Strong distributed systems grounding across queues, async processing, caching, and horizontal scaling
• Practical experience with containers, CI/CD, infrastructure as code, and observability tooling
• Clear written communication and the judgment to balance accuracy, latency, and cost when there is no obvious right answer

Benefits

• Earlier visibility into opportunities
• Better-fit introductions
• Access to meaningful work
• Less application noise
• A network that improves over time