Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Tailor your resume to this Research Engineer, AI Security role.
Rezi rewrites your resume against Tolmo's job description. Free.
Tailor your resume to this Research Engineer, AI Security role.
Rezi rewrites your resume against Tolmo's job description. Free.
Don't guess if your resume is good enough.
See how it scores against the Research Engineer, AI Security posting at Tolmo — free, in seconds.
Don't guess if your resume is good enough.
See how it scores against the Research Engineer, AI Security posting at Tolmo — free, in seconds.
About the Role
As a Research Engineer on AI Security, you will improve the judgment of our AI agents, focusing on how they plan, reason over production systems, identify valuable tests, and validate findings. This role bridges research and engineering, with work shipping directly to production.
Responsibilities
- Improve agent reasoning, planning, tool usage, and graph traversal for faster, more accurate findings.
- Build evals, benchmarks, and graders to measure agent improvements and integrate them into the shipping process.
- Compare models, prompts, and agent designs based on cost, latency, and quality for production decisions.
- Defend agents against prompt injection, data exfiltration, and manipulation; research LLM application security.
- Ensure long-running agents are dependable across thousands of runs through verification, self-checks, and sensible stopping.
- Analyze agent runs from customer engagements to identify reasoning failures and implement fixes and new evals.
Requirements
- Hands-on experience building, evaluating, or improving LLM-based agents or systems in production.
- A rigorous, empirical approach to experimentation and evaluation.
- Strong engineering skills with production-quality code (Python, TypeScript, or Go).
- A working understanding of security or a strong drive to learn it quickly.
- Familiarity with LLM security risks like prompt injection, jailbreaks, and tool misuse.
- Daily use of AI coding agents (e.g., Claude Code, Cursor) with opinions on their reliability.
Skills
- Python
- TypeScript
- Go
- LLM-based agents
- Prompt injection
- Jailbreaks
- Tool misuse
- AI coding agents
Location
- San Francisco
Work Type
- Onsite
- Full-time
Experience Level
- Early-stage startup experience
Education Level
- Research background in machine learning, AI safety, or security (publications, open-source work, or talks) - Nice to have
- Offensive security experience (penetration testing, red teaming, bug bounty, or CTFs) - Nice to have
- Experience with reinforcement learning, fine-tuning, or synthetic data generation for agents - Nice to have
- Experience with graph data models or reasoning over structured data - Nice to have
Salary/Compensations
- Competitive salary, depending on level and experience.
Benefits
- Early-stage equity
- Comprehensive medical, dental, and vision coverage
- Equipment needed to do your best work
About the Company
- Tolmo is a cybersecurity company focused on AI-driven security solutions.
- We are building a new security playbook using AI agents that continuously test production systems.
- Our founders previously built and sold Sqreen to Datadog.
- We are backed by Accel and Y Combinator.
Equal Opportunity
- Tolmo is building a team with wide-ranging backgrounds, perspectives, and paths into security.
- We are an equal opportunity employer and welcome applicants of every background.