About Tolmo
Tolmo is cybersecurity for the age of AI. Coding agents now ship software faster than any human team can review or secure it; 100+ pull requests per engineer per week is no longer an outlier, and attackers are using the same agents to find and exploit weaknesses in days, not months. The old playbook of quarterly pentests and endless alert queues breaks at this speed.
We're building a new security playbook. Tolmo runs a fleet of AI security agents that reason over a live graph of your entire production system (code, CI, cloud, and telemetry) and continuously attack a faithful copy of it like a real adversary. Every finding arrives validated, with its blast radius and a remediation plan that lands in your workflow, ready for a coding agent to fix. Hours to integrate, days to your first validated finding.
We've done this before: Tolmo's founders built Sqreen (acquired by Datadog) and led security products that thousands of organizations trusted. We're backed by Accel and Y Combinator and just getting started.
The role
Our product is only as good as our agents' judgment. As a Research Engineer on AI Security, you make that judgment better and measurably so: how our agents plan, reason over a graph of a customer's production system, decide what is worth testing, and know when a finding is real.
This sits between research and engineering. In one week you might design an eval that catches a new class of false positive, change how an agent plans a multi-step investigation, compare models on a hard benchmark, and harden the agents themselves against prompt injection from the systems they inspect. You'll work directly with the founders, our engineers, and the security leads who run pentests with our agents, and your work ships to production.
What you'll do
Agent reasoning: improve how our agents plan, use tools, and reason over a live graph of code, cloud, and telemetry, so they reach real findings faster and with fewer dead ends.
Evaluation: build the evals, benchmarks, and graders that tell us whether an agent actually got better, and make them part of how every change ships.
Model selection and tuning: compare models, prompts, and agent designs on cost, latency, and quality, and turn the results into production decisions.
Model and agent security: defend our agents against prompt injection, data exfiltration, and manipulation by the very systems they test, and research the security of LLM-based applications our customers build.
Reliability at scale: make long-running agents dependable across thousands of runs: verification, self-checks, and sensible stopping.
Learning from the field: study agent runs from customer engagements, find where reasoning broke, and turn each failure into an eval and a fix.
What we're looking for
Hands-on experience building, evaluating, or improving LLM-based agents or systems in production.
A rigorous, empirical approach: you design experiments, distrust single anecdotes, and let the evals decide.
Strong engineering skills: you write production-quality code (Python, TypeScript, or Go) and build tools other people rely on.
A working understanding of security, or a strong drive to learn it fast: how real systems are attacked and how findings are validated.
Familiarity with LLM security risks such as prompt injection, jailbreaks, and tool misuse.
You build with AI coding agents daily (e.g., Claude Code, Cursor) and have opinions about what makes them reliable.
Nice to have
Research background in machine learning, AI safety, or security: publications, open-source work, or talks.
Offensive security experience: penetration testing, red teaming, bug bounty, or CTFs.
Experience with reinforcement learning, fine-tuning, or synthetic data generation for agents.
Experience with graph data models or reasoning over structured data.
Prior early-stage startup experience.
Compensation & benefits
Competitive salary, depending on level and experience.
Early-stage equity: you're joining early; you'll own a real piece of what we build.
Comprehensive medical, dental, and vision coverage, and the equipment you need to do your best work.
Based in San Francisco; we work in person.
Tolmo is building a team with wide-ranging backgrounds, perspectives, and paths into security; we think it makes our product and judgment better. If you're excited about this role but don't match every point above, we'd still like to hear from you. We're an equal opportunity employer and welcome applicants of every background.