Member of Technical Staff (Applied AI Engineer, Agent Capabilities)
Perplexity · San Francisco
About this role
## Perplexity — Member of Technical Staff (Applied AI Engineer, Agent Capabilities) Perplexity is building the next era of **agentic AI**. The **Agent Capabilities** team sits at the intersection of frontier AI research and product innovation—turning emerging model breakthroughs into **reliable, scalable, high-quality agent capabilities** for both users and agents. This is a highly leveraged role with broad ownership across **agent systems, platform engineering, and product innovation**. ### Tech Stack Python | Go | Rust | PostgreSQL | DynamoDB | AWS | TypeScript ### Why Perplexity is Different - **Craftsmanship** — build high quality, tasteful products for both AI-native and AI-curious users - **Ownership** — identify the problem, design the solution, and ship - **Entrepreneurship** — think like founders, act with urgency, hustle to deliver - **Scholarship** — work with talented peers to pursue knowledge and truth - **Partnership** — amplify strengths, break down silos, and help colleagues deliver excellence ### What You’ll Do - **Evaluate frontier models** on real user tasks; identify useful behaviors and failure modes; turn promising advances into production agent systems - Own the lifecycle from **rapid prototyping & 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/LLM techniques to build scalable capabilities such as **skills, plugins, artifact generation, tool integration, auto-research, and multi-agent collaboration** - Shape architecture, abstractions, and product experiences that let users and agents compose increasingly sophisticated solutions - Own agent behavior and capabilities **end-to-end** (user-facing products/interfaces through backend services) - Define **offline + online evaluations** for task completion, correctness, safety, latency, cost, and user satisfaction - Iterate across models, prompts, harnesses, and products for different problem spaces - Build **secure, observable, and reliable** agent systems (permissions + safeguards for sensitive actions) - Develop **tracing, replay, and monitoring** so failures are reproducible and actionable - Collaborate with **PM, Data Science, and Research** to identify high-impact opportunities and turn complex behaviors into simple, reliable product experiences - Apply advances in **models, inference, evaluation, and agent architecture** to drive measurable production improvements - Provide technical direction on ambiguous problems; raise the bar via design reviews, mentorship, and technical leadership ### Qualifications - Typically **6+ years** of professional software engineering experience; track record building and owning robust AI-powered, large-scale, user-facing or data-intensive products - Exceptional candidates with less experience and outstanding impact are encouraged to apply - Strong software engineering fundamentals; experience building/operating AI/ML products, backend services, or distributed systems at scale - Experience owning the AI product lifecycle: **data analysis, rigorous evaluation, production monitoring, iterative improvement** - Ability to define metrics and use production data + user feedback to guide decisions - Practical experience in one or more areas such as **agent harnesses, tool use, context engineering, model evaluation, browser automation, or long-running task ex
Listing freshness
CronJobs last confirmed this listing 23h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.