Building Expert Search Systems

Key Role : AI Systems Engineer

We provide a platform for researchers globally, from PhD students to academic professionals, to access comprehensive cited reviews in minutes. Our system understands how papers connect, ranks relevance, summarizes insights, and maps citations, removing weeks of manual work.

Our mission is to streamline every stage of academic discovery by building an integrated AI research suite that accelerates science in medicine, AI, climate, and more.

Main Responsibilities :

• Build and optimize semantic search pipelines, graph-based retrieval systems, and agentic systems.
• Design and deploy scalable APIs and services capable of serving hundreds of concurrent requests.
• Architect, implement, and productionize vector databases and embedding-based retrieval systems.
• Work on GenAI integrations, including react agents, graph agents, prompt engineering, and LLM orchestration.
• Set up full-stack search engines from scratch that can handle real-world academic workloads.

This is a hands-on role with real ownership, you will move fast, experiment, and ship production systems that impact thousands of researchers worldwide. Requirements : Strong background in semantic search, vector databases, LLM frameworks, agent-based systems, and document retrieval. Skilled in Python for backend development with the ability to build scalable APIs and services. Past experience deploying systems at scale, including search engines, retrieval pipelines, or embedding models. Ability to design infrastructure that serves hundreds of concurrent requests. Experience setting up and hosting APIs with public access while balancing speed, cost, and reliability. A research-driven and pragmatic mindset with a focus on measurable outcomes.