3 months ago
Base Salary
$185k - $230k/yr
Responsibilities
- Build AI-agent experiences for Otter AI Chat that support reasoning over conversations, knowledge retrieval, and complex task completion.
- Improve the conversational knowledge engine through knowledge extraction, annotation, and indexing.
- Develop evaluation datasets, automated graders, regression tests, and release gates for AI quality.
- Diagnose failures across models, prompts, retrieval, tools, data pipelines, backend services, and product workflows.
- Build shared agent infrastructure for orchestration, tracing, debugging, retries, sandboxed execution, and observability.
- Improve task completion, correctness, groundedness, reliability, latency, and cost.
- Use production traces, customer feedback, and usage signals to drive measurable product and model improvements.
- Collaborate with AI, product, infrastructure, data, security, and application teams on end-to-end capabilities.
Requirements
- 5+ years of AI agent engineering, machine learning engineering, or related experience.
- Strong backend or distributed-systems engineering skills.
- Hands-on experience building and shipping AI-agent or LLM-powered products.
- Experience evaluating nondeterministic systems with a strong focus on AI quality.
- Ability to use data, traces, logs, and qualitative examples to diagnose complex failures.
- Ability to work across services, technical domains, and organizational boundaries.
- Strong product judgment, rigorous engineering practices, and evaluation skills.
- Ability to take ambiguous problems from exploration through production launch and continuous improvement.
- Experience using coding agents effectively while rigorously reviewing and controlling their output is a plus.
Benefits
- Hybrid work arrangement is indicated by the #LI-Hybrid designation.
- The role includes a comprehensive total rewards package, with base salary as one component.
Categories
About Otter.ai
Otter.ai builds an AI meeting assistant that records, transcribes, and summarizes meetings and generates action items for teams and professionals. The subscription-based service offers individual, business, and enterprise plans, with apps for web, mobile, and desktop and integrations with Zoom, Google Meet, and Microsoft Teams. Founded in 2016 and headquartered in Mountain View, California, the company is privately held.