RAG Engineer (Remote — Worldwide)

Join Contextual AI to pioneer the next generation of Retrieval-Augmented Generation (RAG) for the world’s largest enterprises. You will build and optimize our Contextual Language Model (CLM) architecture, moving beyond basic vector search to solve complex data grounding and hallucination challenges. This role is critical in scaling our 'RAG 2.0' vision, ensuring our models provide verifiable, high-accuracy responses on massive, proprietary datasets.

- Design and implement end-to-end RAG pipelines that integrate proprietary enterprise data with our Contextual Language Models. - Develop novel retrieval strategies and ranking algorithms to improve the precision of context injection. - Optimize the end-to-end training and fine-tuning processes for RAG-aligned language models. - Build robust evaluation frameworks to measure RAG performance, grounding, and factual accuracy. - Collaborate with the research team to transition state-of-the-art breakthroughs into production features. - Scale our vector database infrastructure to handle billions of embeddings with low-latency retrieval. - Implement data privacy and security measures to ensure safe handling of sensitive corporate information.

- Strong foundation in NLP and deep learning, specifically with Transformer-based architectures and LLMs. - Proven experience building and deploying production-grade RAG systems or vector search infrastructures. - Expertise in advanced retrieval techniques such as hybrid search, cross-encoders, and query expansion. - Proficiency in Python and modern ML frameworks like PyTorch or JAX. - Experience working with distributed systems and large-scale data processing pipelines. - Capability to work autonomously in a fully remote, global team environment. - Background in optimizing model performance for latency and throughput in enterprise environments.

Equity, healthcare, compute budget.