Asks for

The ad says“Depth in at least one hard surface: LLM agent systems, browser or Chromium internals, OS sandboxing and native clients, or backend and cloud infrastructure — and the excitement to learn the rest”
The ad says“Depth in at least one hard surface: LLM agent systems, browser or Chromium internals, OS sandboxing and native clients, or backend and cloud infrastructure — and the excitement to learn the rest”
The ad says“Depth in at least one hard surface: LLM agent systems, browser or Chromium internals, OS sandboxing and native clients, or backend and cloud infrastructure — and the excitement to learn the rest”
The ad says“Depth in at least one hard surface: LLM agent systems, browser or Chromium internals, OS sandboxing and native clients, or backend and cloud infrastructure — and the excitement to learn the rest”
The ad says“8+ years in offensive security — vulnerability research, exploit development, red teaming, or product security testing — with a record of finding real bugs in software other people had already reviewed”
The ad says“You write production-quality code in one or more of Go, TypeScript, Python, or Swift. You’d rather build the thing that finds a bug a thousand times than find it once”
The ad says“Depth in at least one hard surface: LLM agent systems, browser or Chromium internals, OS sandboxing and native clients, or backend and cloud infrastructure — and the excitement to learn the rest”
The ad says“Practical fluency using LLMs as instruments, not just as targets, plus a working sense of when their output is noise”
The ad says“Depth in at least one hard surface: LLM agent systems, browser or Chromium internals, OS sandboxing and native clients, or backend and cloud infrastructure — and the excitement to learn the rest”
The ad says“Depth in at least one hard surface: LLM agent systems, browser or Chromium internals, OS sandboxing and native clients, or backend and cloud infrastructure — and the excitement to learn the rest”
The ad says“8+ years in offensive security — vulnerability research, exploit development, red teaming, or product security testing — with a record of finding real bugs in software other people had already reviewed”
The ad says“You write production-quality code in one or more of Go, TypeScript, Python, or Swift. You’d rather build the thing that finds a bug a thousand times than find it once”
The ad says“8+ years in offensive security — vulnerability research, exploit development, red teaming, or product security testing — with a record of finding real bugs in software other people had already reviewed”
The ad says“You write production-quality code in one or more of Go, TypeScript, Python, or Swift. You’d rather build the thing that finds a bug a thousand times than find it once”
The ad says“You write production-quality code in one or more of Go, TypeScript, Python, or Swift. You’d rather build the thing that finds a bug a thousand times than find it once”
The ad says“8+ years in offensive security — vulnerability research, exploit development, red teaming, or product security testing — with a record of finding real bugs in software other people had already reviewed”

Dia is a browser enhanced with agentic capabilities. The agent reasons over untrusted content from the open web and takes real actions on the user’s behalf, inside a client that sits next to everything the user is signed into
That combination produces a threat model that mostly doesn’t have prior art — the interesting bugs aren’t on a checklist, and the tooling to find them largely doesn’t exist yet
As a Staff Security Researcher on our security team, you’ll do original offensive research against Dia including the client, agent runtime, tools and integrations it calls, and services behind them. You’ll work ahead of the product, threat modeling new surfaces with the teams designing them, and reviewing features before they reach users
You’ll also eliminate bug classes by building model-driven scanning, fuzzing, and agentic hunting systems that run continuously against our code, our infrastructure, and our agent
You’ll partner closely with the engineers who own remediation, rather than owning the fixes yourself. You’ll report to the Head of Security and work across client, infrastructure, and product engineering
Run original offensive research against Dia, its agent, and backend services, focusing on prompt injection and indirect exfiltration, tool-call abuse, permission and provenance bypass, sandbox escape, cross-profile data access, quota and abuse-scoring bypass
Threat model new surface areas with the teams building them, and review features before they ship, identifying what is exploitable, what it costs an attacker, and what would have to be true to launch
Design and build automated vulnerability discovery including model-driven code and infrastructure scanning, fuzzing harnesses, and agentic hunting pipelines that keep working after the engagement ends
Eliminate entire classes of bugs in collaboration with the engineers who own the fix, then make the same issue structurally hard to reintroduce through an enforced invariant, a fail-closed default, a test, a lint, or a platform change
Set the standard for what “security tested” means before a feature ships, and raise the ceiling on what the whole team can find
Continuous AI-assisted vulnerability discovery (first project). You’ll survey commercial scanning services, frontier models, open-source security models, and stand up a working mix against our codebase, our infrastructure, and the agent runtime
Agent red teaming. Plan and run regular AI-assisted red team exercises against Dia and our infrastructure, and build the attack corpus and harness that make each round cheaper than the last
Pre-launch review as a practice. New tools and integrations, agent capabilities, enterprise controls, platform expansion. Enhanced with platforms to assist with testing
Structural fixes that eliminate classes of vulnerability. Define, with the product engineers, the changes that take a whole bug class off the table instead of fixing the same issue one report at a time
Future tools and systems. The state of the art in vulnerability hunting is evolving faster than it ever has. We expect this person to track it and keep BCNY best in class, which means therea re opportunities to build far beyond the scope described above

Benefits

Choose-Your-Own-Compensation Plan: When we give you a job offer, we’ll actually give you two different offers — one that is focused on having a higher salary and one focused on higher equity. Candidates can choose either offer (or any numbers in-between) when they accept.
Best in the Biz Insurance: We provide employees with full coverage medical, vision, and dental insurance and a free One Medical membership to help you keep you and your family healthy. We cover 100% of employee plan costs and up to 90% for dependents.
Napping During the Workday: Some of us are better in the mornings, others are more productive in the afternoon. People should take breaks when they need to. If you’re on our team, we trust you to get your work done — our policy is: work when it makes sense for you!
Take Time Off, Please!: We believe that people do their best work when they’ve rested and had valuable time off. So rather than having a maximum number of days off, we actually have a recommended minimum vacation of 20 days a year. Take time off when you need it and also just when you feel like it.
Extremely Flexible Parental Leave: We are proud to offer an extremely flexible 12 weeks of parental leave — for any parent regardless of gender and for birth, adoption, surrogacy, or fostering. Take the 12 weeks all at once, or split up days to slowly transition back to work — we’re accommodating to everyone’s different situations! Birth mothers also qualify for an additional 6 weeks of medical leave.
Design Your Dream Home Office: We are a remote first company. About half of our team currently lives outside of New York and across 5 different time zones. So if you need some stuff to make working from home a bit easier, we offer a $1000 stipend for anything you need to get comfortable.
Cozy Office in Brooklyn, Wooo!: If you do happen to live in the New York area (or you want an excuse to visit) you can come into our beautiful office in Williamsburg. Coming into office is entirely optional, some of us come almost every day and some of us come in once a week. No obligation, we just genuinely like each other!

Preferred experience

You resonate with our company values
You thrive in a high-trust, high-ambiguity environment: you seek feedback, but you don’t need hand-holding
You write findings engineers act on, and you can stay in the fix conversation and push for the durable version without owning the remediation yourself
Depth in at least one hard surface: LLM agent systems, browser or Chromium internals, OS sandboxing and native clients, or backend and cloud infrastructure — and the excitement to learn the rest
You write production-quality code in one or more of Go, TypeScript, Python, or Swift. You’d rather build the thing that finds a bug a thousand times than find it once
We’re primarily focused on hiring in North American time zones and require that folks have 4+ hours of overlap time with team members in Eastern Time Zone
Practical fluency using LLMs as instruments, not just as targets, plus a working sense of when their output is noise
8+ years in offensive security — vulnerability research, exploit development, red teaming, or product security testing — with a record of finding real bugs in software other people had already reviewed

Recruitment process

Deadline to Apply: 31 December 2026 at 08:00 GMT