What you'll do- Design and ship new agent capabilities for Nexus - new tools, skills, integrations, and conversational flows that meaningfully expand what users can accomplish through chat.
- Build and own production-grade Python services (FastAPI, async patterns) that power Nexus's agent runtime, tool execution, and orchestration logic.
- Extend our orchestration layer (LangGraph / LangChain or equivalent) with new agent topologies, routing logic, and tool-use patterns.
- Design tool-use and function-calling interfaces - including MCP servers - that let Nexus safely interact with Arlo platform APIs, device telemetry, and partner systems.
- Build the evals and observability that make agent behavior measurable: offline test suites, online quality metrics, trace tooling, regression detection, and dashboards engineers and PMs actually use.
- Own the testing strategy for AI experiences - design and build the test harnesses, golden datasets, scenario suites, adversarial/red-team tests, and CI gates that catch agent regressions before they reach users. Define what "good" looks like for conversational quality, tool-use correctness, and task completion.
- Partner closely with product, design, and platform teams to turn user needs into shipped agent features - and bring engineering judgment to scoping, sequencing, and tradeoffs.
- Set technical direction for agent development practices at Arlo: patterns, frameworks, code review standards, and the playbook other engineers follow when they build on Nexus.
- Mentor mid and senior engineers on LLM systems, prompt design, and production AI engineering.
What we're looking forMust-haves- 8+ years of software engineering experience, with at least 1-2 years building production LLM-powered systems - ideally agentic chat, copilots, or multi-step agent workflows.
- Strong production Python - FastAPI, asyncio, type hints, testing discipline. You've built and operated Python services at meaningful scale.
- Hands-on experience with LLM orchestration frameworks like LangGraph, LangChain, LlamaIndex, or equivalent - and an opinion on when to use them vs. build your own.
- Deep familiarity with tool-use / function-calling patterns. Bonus if you've built or integrated MCP (Model Context Protocol) servers, but strong tool-use experience in any framework translates.
- Experience designing multi-agent or multi-step workflows: planner/executor patterns, agent handoff, state management, error recovery, human-in-the-loop.
- A real point of view on evals and observability for LLM systems - you've built (or fought to build) the feedback loops that keep agents from regressing in production.
- Hands-on experience testing AI/LLM experiences in production - building eval datasets, scoring rubrics (LLM-as-judge, human-in-the-loop, deterministic checks), regression suites, and the discipline to know which one applies when. You understand why traditional unit tests aren't enough for non-deterministic systems and have built the testing patterns that fill the gap.
- Track record of shipping at the Staff level - you've operated as a technical leader across teams, not just an individual contributor with a senior title. The bar is delivery and influence, not slide decks.
Nice-to-haves- Experience with RAG, vector databases, embedding pipelines, and retrieval quality tuning.
- Familiarity with Anthropic's Claude API, OpenAI's Responses API, or comparable provider SDKs at the level of tool use, structured outputs, and streaming.
- Experience instrumenting LLM systems with tools like LangSmith, Langfuse, Arize, Braintrust, or homegrown tracing.
- Experience with AI testing tooling (Braintrust, Langfuse, Patronus, DeepEval, Promptfoo, or equivalent), or having built homegrown versions of these.
- Familiarity with red-teaming, prompt injection testing, or adversarial evaluation of agent systems.
- Experience building backend systems for IoT or connected devices - reasoning about device state, telemetry streams, intermittent connectivity, command/response patterns, and the kind of real-world messiness that doesn't show up in pure SaaS backends. Bonus if you've designed APIs or agents that operate over a fleet of devices.
- Experience working with mobile clients (iOS / Android) as API consumers of an agent backend.
- Prior work on prompt engineering at scale, including prompt versioning, A/B testing, and prompt regression frameworks.
The pay range for this position reflects the minimum and maximum target for new hire salaries at commencement of employment and is expected to be between USD$175,000 - $225,000/year. However, base pay offered may vary depending on multiple factors, including role, job-related knowledge, skills, relevant education and experience.
We're committed to inclusivity and selecting the strongest candidate-no matter their background. Even if you don't meet every listed qualification, we encourage you to apply. We're happy to support growth in areas essential to the role. Interested in learning more about our workplace? Visit and follow our LinkedIn, and Glassdoor pages to read employee insights and get updates of what it's like to be part of Arlo.
