AI Application Backend Development Engineer (Token Platform)
Summary
Backend engineer (3–5 yrs) building services for an AI and token platform: LLM integration and model routing, token metering/quota and billing, RAG pipelines (embeddings, vector search, reranking) and AI agents with Function Calling. Stack includes Python/Java/Go/Node.js with MySQL/PostgreSQL/Redis/MongoDB.
Salary: $7,000 – $9,000 per month
About the role
We are seeking experienced Backend Engineers to develop and maintain backend services for our AI and Token platform. You will work on LLM integration, model routing, Token metering, knowledge retrieval and AI agent capabilities.
Key responsibilities
Design and develop backend services for AI conversations, knowledge bases, AI agents and model APIs.
Build model integration and routing capabilities, including streaming responses, timeouts, retries and failover.
Develop Token metering, usage tracking, quota management, cost calculation and billing reports.
Implement user accounts, tenant isolation, authentication, rate limiting and usage records.
Develop RAG workflows, including document parsing, embeddings, vector search and reranking.
Build backend capabilities for AI agents, Function Calling and tool usage.
Improve performance, security, availability, monitoring, logging and cost efficiency.
Collaborate with product, frontend and overseas teams on technical integration and documentation.
About you
Bachelor's degree or above in Computer Science, Software Engineering or a related field.
3–5 years or above of relevant experience.
Proficiency in at least one of Python, Java, Go or Node.js.
Familiarity with RESTful APIs, microservices and database design.
Understanding of LLMs, Prompt Engineering, RAG, AI agents and Function Calling.
Experience with LLM API integration, streaming responses, timeout handling and retries.
Familiarity with at least one of MySQL, PostgreSQL, Redis or MongoDB.
Knowledge of vector databases, asynchronous programming and message queues is preferred.