Real-world Feedback Loops: Leverage multi-channel user feedback and real-world task data as primary research signals; design experiments and datasets to continuously improve agent and retrieval performance in production scenarios
1+ Year hands-on experience with LLM, RAG and AI agent systems in production
RAG & Agentic RAG Engineering: Hands-on experience building production retrieval pipelines end-to-end — embedding models (BGE, OpenAI, etc.), vector stores (Qdrant, Milvus, Pinecone, Weaviate), hybrid search (keyword + vector), reranking models; deep understanding of chunking strategy, text cleaning, and multimodal data parsing; experience implementing Agentic RAG patterns — Self-RAG, Corrective RAG, adaptive retrieval, multi-hop decomposition, retrieve-reflect-refine loops
...
Lead the development of core content recommendation modules using data-driven strategies to maximize content value and user impact.
Collaborate with content, business, and product management teams to identify needs and opportunities within content scenarios, and jointly define success metrics.
MSc or PhD in Machine Learning, Computer Vision, Computer Science, or Applied Mathematics, with at least 5 years of relevant industry experience (experience in the content domain is preferred).
...
Real-world Feedback Loops: Leverage multi-channel user feedback and real-world task data as primary research signals; design experiments and datasets to continuously improve agent and retrieval performance in production scenarios
1+ Year hands-on experience with LLM, RAG and AI agent systems in production
RAG & Agentic RAG Engineering: Hands-on experience building production retrieval pipelines end-to-end — embedding models (BGE, OpenAI, etc.), vector stores (Qdrant, Milvus, Pinecone, Weaviate), hybrid search (keyword + vector), reranking models; deep understanding of chunking strategy, text cleaning, and multimodal data parsing; experience implementing Agentic RAG patterns — Self-RAG, Corrective RAG, adaptive retrieval, multi-hop decomposition, retrieve-reflect-refine loops
...
Act as a full stack "seed" within your team — champion full stack practices, mentor peers, and help scale AI-augmented development across the organization
Proactively identify efficiency bottlenecks in cross-team collaboration and propose improvements to product, design, and engineering processes
Contribute to the full product lifecycle — from ideation and design to deployment and iteration
...
Write and maintain automated tests and CI/CD-related configurations to improve development efficiency and code quality.
Support the engineering deployment of AI/LLM capabilities based on business needs, such as integrating LLM APIs, building basic RAG pipelines, and embedding tool/agent capabilities into existing systems.
Help build and maintain datasets and benchmarks for evaluation/regression, track online performance, and assist with debugging and fixing issues.
...