about the company. A high-growth global e-commerce and technology leader that is seeking visionary AI talent to shape the future of smart ecosystem services. Driven by a massive global footprint and an unmatched data repository, we empower top engineers, researchers, and data scientists to build cutting-edge machine learning models that impact millions of users daily. about the team. a diverse, highly collaborative group of machine learning engineers, data scientists, and researchers dedicated to transforming massive, real-world data into intelligent, high-impact user experiences.
Operating within a global tech powerhouse, our team combines the agile, experimental mindset of a startup with the computing resources and data infrastructure of a worldwide leader. about the job. Platform Architecture: Design and implement a centralized coding harness that integrates generative AI with internal developer systems (e.g., version control, code search, documentation, ticketing, and deployment pipelines).
Intelligent Workflows: Build and optimize RAG pipelines over complex codebases and technical documentation to deliver accurate, context-aware code suggestions, reviews, and technical Q&A. Agentic Systems: Develop autonomous coding agents capable of performing complex tasks such as refactoring, bug fixing, test generation, and automated pull request reviews, operating securely within existing access-control frameworks.
Efficiency & Cost Management: Engineer mechanisms for model routing, prompt caching, request throttling, and usage monitoring to ensure sustainable inference costs at an enterprise scale. Security & Governance: Enforce comprehensive security standards, including automated secret redaction, granular access scoping, comprehensive audit logging, and policy-as-code guardrails. Developer Surface Integration: Embed the harness into daily developer touchpoints—including IDE extensions, CLI tools, and PR bot workflows—to ensure seamless adoption.
Performance Engineering: Develop benchmarking tools to evaluate accuracy, latency, and developer satisfaction, driving continuous iteration of the platform. Research & Innovation: Stay at the forefront of AI engineering by applying cutting-edge techniques such as speculative decoding, specialized tool-use agents, and advanced context compression. skills and experience required. 3+ years of professional experience in software engineering, with a strong focus on LLM application development, platform engineering, or developer tooling.
Proven expertise in building production-grade AI applications using prompt engineering, RAG, function calling, and agentic workflows. Strong proficiency in Python or Go, with a track record of building and scaling backend services and APIs. Experience integrating with developer ecosystem tools (Git APIs, IDE extension frameworks, CI/CD pipelines). Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
Hands-on experience with LLM frameworks (e.g., LangChain, LlamaIndex, vLLM) and vector search/retrieval systems. Experience in inference cost optimization and model routing strategies. Knowledge of agentic coding protocols (e.g., Model Context Protocol, function-calling patterns). Experience developing IDE integrations (e.g., VS Code extension API, Language Server Protocol). Familiarity with observability tools for LLMs (e.g., Langfuse, tracing, prompt regression testing).
Experience with Kubernetes and cloud-native deployment patterns. 工作经验 Agent harness