We are seeking a proactive and talented Senior Lead NLP / AI Engineer to join our AdTech team. In this role, you will be instrumental in transforming raw advertising text into actionable intelligence - extracting keywords, intent, and semantic meanings, and generating high-dimensional vector embeddings to drive our CTR/CVR prediction models and ad-triggering engines. Beyond core ad data processing, you will also play a key role in driving internal efficiency by building AI Agents and automated workflows to streamline repetitive engineering processes within the team.
What you will do
- Ad Text Processing & Feature Extraction: Build and maintain scalable pipelines to process unstructured ad content (titles, descriptions, keywords) and extract key signals such as topics, intent, and semantic meanings;
- Vector Embedding Generation: Convert textual data into dense vector embeddings to serve as high-quality feature inputs for downstream Machine Learning models;
- Model Integration & Ad Targeting: Feed extracted features and embeddings into CTR (Click-Through Rate) and CVR (Conversion Rate) prediction models, as well as real-time Ad Triggering & Semantic Matching engines;
- Internal Process Automation via AI Agents: Research, design, and deploy internal AI Agents and automated workflows to automate repetitive operational tasks and data processing routines within the team.
What you will need
- Domain & Technical Experience: Proven experience in NLP and Feature Engineering, ideally within AdTech, Search, E-commerce, or Recommendation Systems;
- NLP & Embedding Expertise: Strong hands-on experience with text vectorization techniques (e.g., Sentence-Transformers, Hugging Face models, BGE, OpenAI embeddings) and keyword/entity extraction;
- Ad-Model Understanding: Clear understanding of how textual features and vector representations impact CTR/CVR predictive models and vector-based ad retrieval/matching algorithms;
- AI Agent & Automation Skills: Practical experience or strong familiarity with AI Agent frameworks and orchestration tools (e.g., LangChain, LlamaIndex, CrewAI, AutoGen, n8n, or Dify);
- Tech Stack: Proficiency in Python, standard ML/NLP libraries (PyTorch, TensorFlow, SpaCy, Hugging Face), and experience working with Vector Databases (e.g., Qdrant, Pinecone, Milvus, FAISS).
Nice To Have
- Experience optimizing GPU infrastructure, model quantization, and distillation;
- Experience building MCP servers/tool libraries;
- Experience with audit trail and compliance systems for AI in large enterprise environments.
