MVA LLM Developer 奔驰虚拟助手开发工程师

Mercedes-Benz Group China Ltd.

Mercedes-Benz Group China Ltd., Beijing (Hybrid)

Job Type Full time

Experience 3+ years

Posted 3 weeks 6 days ago

Hybrid 3+ years Level

Tasks

Design and develop the next-generation in-car MVA Agent architecture, including:

Build agentic systems with design patterns such as ReAct, Plan-and-Execute, and Tool Calling / Function Calling.
Integrate LLM provider APIs and implement multi-model orchestration and routing strategies.
Develop conversational memory services covering short-term dialogue context and long-term user profiling.
Design and implement standardized tool-calling interfaces for vehicle capabilities.
Perform prompt engineering, RAG pipeline development, and model evaluation to continuously optimize AI quality.
Conduct unit testing, integration testing, and AI-specific evaluation, including evaluation datasets and A/B testing.
Submit and deploy code via CI/CD pipelines on Azure cloud.

Drive cross-team technical alignment and solution design as the technical owner for the Agent architecture.

Produce and maintain system architecture proposals, interface design documents, and technology selection reports, including architecture proposals for new Agent features, API specifications, tool-calling schemas, AI system behavior documentation, prompt versioning, and evaluation results.

Continuously improve AI development methodologies and toolchains by evaluating new LLM capabilities, Agent frameworks, and AI coding tools such as Cursor, Copilot, and Claude Code; monitoring production performance; tracking AI quality metrics; and driving post-go-live optimization.

Qualifications

Bachelor's degree or above in Computer Science, Software Engineering, Artificial Intelligence, or a related field.
At least 3+ years of experience in LLM application development, AI Agent development, or similar AI engineering roles.
Hands-on experience building AI Agent systems from scratch and familiarity with ReAct, Plan-and-Execute, Tool Calling / Function Calling, and agent memory management.
Familiarity with an agent orchestration framework such as LangChain, LangGraph, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, Dify, or Coze.
Understanding of mainstream LLM capabilities and limitations; multi-model orchestration and routing experience is a plus.
Proficiency in prompt engineering, structured output generation, and guardrails.
Proven RAG project experience with vector databases, embeddings, chunking, hybrid search, and re-ranking.
Experience designing AI evaluation metrics, A/B testing, and evaluation pipelines.
Understanding of short-term conversational context and long-term user profiling or episodic memory.
Strong Python programming skills; Go experience is a plus.
Proficiency in cloud technology, microservices, API design, and cloud-native deployment on Azure.
Ability to produce system architecture proposals, interface design documents, and technology selection reports independently.
Proficiency with AI-assisted programming tools such as Cursor, GitHub Copilot, or Claude Code.
Strong ownership mentality, self-driven teamwork, and excellent communication skills.
Good English communication skills; German is a plus.

Benefits

Employee events, flextime, possible hybrid work, health benefits, mobility offers, employee discounts, possible public transport support, a barrier-free workplace, parking, an in-house doctor, and a canteen and café.