Senior Staff AI Engineer, Frontier Agent Capabilities

Perplexity; San Francisco (CA); On-site; USD 220,000 - 405,000; Full time

Job summary

Perplexity Computer seeks a senior software engineer to join the Agent Capabilities team, turning frontier AI breakthroughs into reusable product capabilities. You will own end-to-end agent systems, from rapid prototyping to production, with a strong emphasis on planning, tool use, and reliability.

You will apply state-of-the-art ML/LLM techniques to design scalable capabilities, collaborate with PM/Data Science/Research, and shape architectures that empower users and agents to solve complex

Qualifications

• 6+ years of professional software engineering experience with AI-powered, large-scale, user-facing or data-intensive products.
• Strong fundamentals; experience building and operating AI/ML products, backend services, or distributed systems at scale.
• Experience owning the AI product lifecycle, including data analysis, rigorous evaluation, production monitoring, and iterative improvement.
• Able to define metrics and use production data and user feedback to guide decisions.
• Practical experience in agent harnesses, tool use, context engineering, model evaluation, browser automation, or long-running task execution.
• Strong product judgment and execution: translate ambiguous user needs into applied AI/ML problems and ship durable solutions with measurable impact.
• Genuine interest in frontier AI capabilities, agent systems, and exploration/productization of new model behaviors.

Responsibilities

• Evaluate frontier models against real user tasks, identify useful behaviors and failure modes, and turn the most promising advances into production agent systems. Own the lifecycle from rapid prototyping and evaluation through launch, monitoring, and iteration.
• Improve agents’ ability to plan, use tools, manage context, recover from errors, and complete long-running tasks reliably.
• Apply state of the art ML and LLM techniques to design scalable agent capabilities such as skills, plugins, artifact generation, tools integrate and use, auto-research, and multi-agent collaboration. Shape the architecture, abstractions, and product experiences that enable both users and agents to compose increasingly sophisticated solutions for real-world tasks.
• Own agent behavior and capabilities end-to-end, from user-facing products and interfaces to backend services. Define offline and online evaluations for task completion, correctness, safety, latency, cost, and user satisfaction. Iteratively improve across models, prompts, harnesses, and products for different problem spaces.
• Build secure, observable, and reliable agent systems, including permissions and safeguards for sensitive actions. Develop tracing, replay, and monitoring infrastructure that makes agent failures reproducible and actionable.
• Collaborate closely with PM, Data Science, Research, to identify high-impact opportunities in understanding and validating emerging model capabilities, and turn complex agent behaviors into simple, reliable product experiences.
• Apply relevant advances in models, inference, evaluation, and agent architecture when they produce measurable improvements in production performance. Set technical direction on ambiguous problems and raise the bar through design reviews, mentorship, and technical leadership.

Skills

Software engineering

AI/ML products

Distributed systems

Data analysis

Model evaluation

Product lifecycle

Job description

Perplexity Computer seeks a senior software engineer to join the Agent Capabilities team, turning frontier AI breakthroughs into reusable product capabilities. You will own end-to-end agent systems, from rapid prototyping to production, with a strong emphasis on planning, tool use, and reliability.

You will apply state-of-the-art ML/LLM techniques to design scalable capabilities, collaborate with PM/Data Science/Research, and shape architectures that empower users and agents to solve complex