ML/AI Engineer

Join Endee as an ML/AI Engineer to architect and build the intelligence layer of our vector database. You will design embedding pipelines, implement state-of-the-art similarity search algorithms, and develop AI-powered features that serve millions of queries per second. This role sits at the intersection of applied research and production engineering: you will ship models that directly impact how developers build AI applications.

• Research, prototype, and productionize cutting-edge vector search and approximate nearest neighbor (ANN) algorithms
• Design and optimize end-to-end embedding pipelines for low-latency, high-throughput inference
• Build evaluation frameworks and automated benchmarking suites for search quality and retrieval accuracy
• Develop retrieval-augmented generation (RAG) integrations and semantic search capabilities
• Collaborate with the core database team to co-design indexing structures optimized for ML workloads
• Partner with customers and developer advocates to translate real-world AI use cases into product features

• 3+ years of hands-on experience in ML/AI, with production deployment experience
• Deep proficiency in Python; experience with C/C++ for performance-critical components is a strong plus
• Expertise with embeddings, vector search, information retrieval, or recommendation systems
• Solid understanding of transformer architectures, attention mechanisms, and modern LLM pipelines
• Experience with PyTorch, TensorFlow, or JAX in production settings
• Strong fundamentals in linear algebra, probability, and algorithm design