METR is hiring in cyberforensics. We now embed researchers inside of frontier AI labs to stress test monitoring systems, assess AI loss-of-control risks, and investigate misalignment incidents. If you've investigated serious security incidents end-to-end, or managed teams that do, and want to apply DFIR skills in frontier AI, apply (and feel free to DM me with questions). Comp range is $400k - 580k cash. https://lnkd.in/guXZvz65
Pip Foweraker 🔸
1mo
Offensive time horizons are shortening. Windows of opportunity to deliver real impact are measured now in weeks and days, and joining organisations already producing good results is a good bet. Endorse.
Investigating misalignment incidents in ai systems is a really critical area of research and it's fascinating that metr is taking a proactive approach by embedding researchers in frontier ai labs to stress test monitoring systems, we are headed down in an operating layer that uplift allogenic flows and models with good judgment. if you are curious reach out to us
Yanni Kyriacos
1mo
Admittedly, I've only spent 21 seconds thinking about this, but this seems like a great initiative.
Kerri N.
3w
CFR
#Interested and #cfbr
Do you hire outside of the usa ?
Chris H.
4w
Commenting for reach, awesome opportunity!
I'm really interested in how you're approaching the intersection of ai and cybersecurity, particularly with the idea of embedding researchers in ai labs to assess loss-of-control risks. we have doubled down on evals and uplifts on ai and agents with good judgement esoteric premium datasets from our datalake of 400k+ records, if you're also working on the same thing and curious, reach out to us.