• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
AI
Self-promo

Perplexity seeks engineers for AI agent safety and security work

A Perplexity engineer says the team is building and testing systems aimed at making AI agents safer and more secure.

Aravind SrinivasAS
Andrew Gordon WilsonAG
2 Sources, 11d ago, first seen 11d ago

TLDR

A Perplexity engineer is recruiting people to build and test AI agent safety and security systems. Another post invites engineers who enjoy breaking systems and building guardrails to join the security team, including using frontier AI for that work.

Combined views

44.9K

2 Sources, first seen 11d ago

388 likes30 comments92 saves25 reposts

Combined views

44.9K

2 Sources, first seen 11d ago

388 likes30 comments92 saves25 reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Featured Source

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Related

AI models bypassed network limits in Perplexity’s SPACE sandbox tests

Perplexity says four models reached a blocked destination when its sandbox allowed limited network access. It says it fixed and retested the two bypass methods they used.

Perplexity Research Fellowship offers priority consideration for applications received by September 30, 2026

Perplexity describes the fellowship as a program for early-career STEM talent and says it reviews applications on a rolling basis. A post promoting it highlights architecture design, multi-agent collaboration and synthetic data as research areas.

Perplexity Adds Hybrid Compute to Mac App

Perplexity AI enables tasks to shift from cloud to local models on Mac for private data.

2 Sources

Aravind Srinivas@AravSrinivasConsider joining our security team if you enjoy breaking systems and building guardrails (and using the frontier AI’s to help you do both). Kyle is awesome to work with and writes a lot of code himself!11d
Andrew Gordon Wilson@andrewgwilsRT @kpolley: The best way to predict the future is to invent it. We’re building and testing systems to make AI agents safer and more secur…11d
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    PerplexityAravind Srinivas

    2 Sources

    Aravind Srinivas@AravSrinivasConsider joining our security team if you enjoy breaking systems and building guardrails (and using the frontier AI’s to help you do both). Kyle is awesome to work with and writes a lot of code himself!11d
    Andrew Gordon Wilson@andrewgwilsRT @kpolley: The best way to predict the future is to invent it. We’re building and testing systems to make AI agents safer and more secur…11d
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet