AI Safety Researcher

Careers / AI Safety Researcher
RESEARCHKuala Lumpur
Remote within KL, onsite when needed
Full-time
AI Safety Researcher
Study emerging attack vectors against LLMs and agents. Turn research findings into production detectors and policy primitives.
Apply now →All open roles
Department
RESEARCH
Location
Kuala Lumpur
Remote within KL, onsite when needed
You must be based in Kuala Lumpur / Klang Valley and already have the right to work in Malaysia. Day-to-day work can be remote within KL, but you'll come into our KL office when the business needs it. We do not sponsor visas or relocation.
Type
Full-time
Open to part-time arrangements, and we welcome internship applications for this role.
How to apply
Apply through our short application form. Applications sent by email are not reviewed.
Apply now →
About The Role
Attacks against LLMs and autonomous agents evolve weekly — new jailbreaks, new injection techniques, new exfiltration patterns. As AI Safety Researcher, you’ll track this landscape ahead of our customers, reproduce attacks against real model deployments, and work with engineering to turn findings into detectors that ship into the inspection pipeline within days, not quarters. This is a forward-deployed research role — you may be deployed on-site with customers during pilots and security reviews, for stretches of up to three weeks at a time, advising on emerging risks in person.
What you'll do
Research and reproduce emerging attack techniques against LLMs and autonomous agents — prompt injection, jailbreaks, data exfiltration, tool-call abuse.
Design evaluation suites and red-team harnesses to continuously test Obiguard’s own detectors against novel attacks.
Translate research findings into production detector specs and policy primitives, working closely with the engineering team.
Publish internal and external write-ups on notable findings, contributing to Obiguard’s standing as a research-driven vendor.
Map new attack classes and detectors to relevant compliance frameworks (NIST AI RMF, ISO 42001, EU AI Act).
Advise customers on emerging risks during pilots and security reviews.
What we're looking for
Strong background in ML/NLP, applied security research, or adversarial machine learning — academic or industry.
Hands-on experience prompting, fine-tuning, or red-teaming LLMs.
Comfortable reading and reproducing findings from security research papers and disclosures.
Able to communicate technical findings clearly to both engineers and non-technical stakeholders.
Programming proficiency in Python; comfortable building quick evaluation tooling from scratch.
Comfortable with extended client-site deployments — this is a forward-deployed role, with on-site stints of up to three weeks at a time during active engagements.
Nice to have
Publications or public write-ups on LLM/agent security, adversarial ML, or red-teaming.
Experience with CTFs, bug bounties, or formal security research.
Familiarity with agent frameworks (LangGraph, AutoGen, MCP-based tooling).
Ready to apply?
Apply through our form.
We review every one.
Complete our short application form with your CV and the role you're applying for. Only shortlisted candidates will be notified.
Apply now →See other roles
AI risk governance for organizations shipping LLMs in production. Built by veterans of security, identity, and ML platform.
Governance AIObichatSOC
Platform
InspectionPolicyAllow-listsAudit ledgerEvaluationsEthics & biasFramework mappingAll capabilities →
By Role
For Security TeamsFor Risk & ComplianceFor Platform TeamsFor Agent Teams
Resources
DocsNewsArchitectureOur Security
Company
AboutTeamCareersPressContact
Industries
Health Tech & MedTechFinTech & Financial ServicesStartups & Scale-upsEnterprise & SaaSPublic Sector & GovernmentLegal & Professional ServicesView all industries →
Use Cases
Prompt Injection & Jailbreak DefensePII / PHI / PCI Data RedactionShadow AI DiscoverySecure Employee AI ChatAgentic AI & Tool-Call GovernanceRegulatory Compliance & Audit ReadinessVulnerability & CVE ManagementAlert Response & RemediationView all use cases →
© 2026 OBIGUARD SDN. BHD.
A Malaysia Digital (MD) Status Company
PrivacyTerms

Work arrangement
Yes