We are looking for a Senior AI Software Engineer to build the agents that sit on top of our search platform: systems that take a user's intent, break it into steps, gather and verify information from the web, and return answers an agent can act on. You will work across applied research and engineering, designing how agents plan, call tools, retrieve, and reason so they accomplish open-ended tasks reliably and at scale.
This is a high-ownership role at the intersection of agent systems, retrieval, and product. You will turn frontier-model capabilities into dependable, production-grade agent behavior, and you will own that behavior end to end, from the prompts and tools to the evaluation that proves it works.
In this position, your responsibility will be to
Design and build AI agents that plan, retrieve, and reason over real-world information to complete open-ended tasks
Build the tool interfaces and context engineering that let frontier models use our search and other tools effectively
Mine and analyze usage data to build agents that learn and improve continually from how they are used
Turn new model capabilities into reliable product features, and own them from prototype to production
Define the evaluations, metrics, and guardrails that prove an agent is accurate, grounded, and safe
Improve agent quality across reasoning, planning, tool use, and grounding against real user tasks
Build the backend and infrastructure that run agents reliably under high volume
Collaborate with the search, ML, and product teams to make agent and platform capabilities reinforce each other
Requirements: You may be a good fit if you:
6+ years of software engineering experience, with a track record of shipping complex systems to production
Strong understanding of LLMs and transformer architecture, and how model behavior shapes what agents can do
Able to mine and analyze data to build agents that learn and improve continually
Hands-on experience building agentic systems: tool calling, planning, multi-step or long-running task execution
Experience with agentic frameworks (e.g. LangChain, DeepAgents) and tracing tools (e.g. LangSmith)
Strong grasp of context engineering and tool interfaces for frontier LLMs
Comfortable defining the metrics and evaluations that prove a system works, and iterating on them
Strong product judgment; you turn vague needs into reliable systems and ship without waiting for perfect specs
Thrive in a small, fast-moving team and take ownership end to end
This position is open to all candidates.