Member of Technical Staff (Applied AI Engineer, Agent Capabilities)
$220k - $405k • Remote • San Francisco • FullTime
Posted 1mo ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
AI Engineer
About the job
The Agent Capabilities team at Perplexity Computer is at the forefront of agentic AI, bridging frontier AI research with product innovation. This team builds the foundational capabilities that empower users and agents to tackle increasingly complex tasks. They are responsible for translating cutting-edge AI model breakthroughs into reusable product features, evaluating emerging model capabilities, identifying user value, and transforming these into reliable, scalable, high-quality experiences. This role offers broad ownership at the intersection of AI research, agent systems, platform engineering, and product innovation.
Responsibilities
- Evaluate frontier models against real user tasks, identify useful behaviors and failure modes, and turn promising advances into production agent systems, owning the full lifecycle from prototyping to iteration.
- Improve agent capabilities in planning, tool usage, context management, error recovery, and reliable completion of long-running tasks.
- Apply state-of-the-art ML and LLM techniques to design scalable agent capabilities like skills, plugins, artifact generation, tool integration, auto-research, and multi-agent collaboration.
- Shape the architecture, abstractions, and product experiences that enable sophisticated solutions for real-world tasks.
- Own agent behavior and capabilities end-to-end, defining offline and online evaluations for task completion, correctness, safety, latency, cost, and user satisfaction.
- Iteratively improve models, prompts, harnesses, and products based on evaluation data and user feedback.
- Build secure, observable, and reliable agent systems with safeguards, developing tracing and monitoring infrastructure for reproducibility and actionability.
- Collaborate with PM, Data Science, and Research to identify high-impact opportunities and translate complex agent behaviors into simple, reliable product experiences.
- Apply relevant advances in models, inference, evaluation, and agent architecture for measurable production performance improvements.
- Set technical direction on ambiguous problems and elevate standards through design reviews, mentorship, and technical leadership.
Requirements
- Typically 6+ years of professional software engineering experience with a track record of building and owning robust AI-powered, large-scale, user-facing or data-intensive products.
- Strong software engineering fundamentals, with 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.
- Ability 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, translating ambiguous user needs into applied AI/ML problems and shipping durable solutions with measurable user impact.
- Genuine interest in frontier AI capabilities, agent systems, and excitement for rapidly exploring, evaluating, and productizing new model behaviors.