AI Safety Researcher

Obiguard; Kuala Lumpur; Hybride; MYR 120 000 - 170 000; Plein temps

Résumé du poste

Obiguard is seeking an AI Safety Researcher based in Kuala Lumpur. You will study emerging attack vectors against LLMs and autonomous agents and translate findings into production detectors within the inspection pipeline.

Role involves reproducing attacks, collaborating with engineering to deploy detectors, and publishing insights. You may be deployed on-site with customers during pilots, with remote work possible within Kuala Lumpur.

Qualifications

• Strong background in ML/NLP or applied security research, academic or industry.
• Hands-on experience prompting, fine-tuning, or red-teaming LLMs.
• Able to read and reproduce security research findings and disclosures.
• Capable of communicating complex results to engineers and non-technical stakeholders.
• Proficient in Python and able to build quick evaluation tooling.

Responsabilités

• Research and reproduce emerging attack techniques against LLMs and autonomous agents; prompt injection, jailbreaks, data exfiltration.
• Design evaluation suites to continuously test detectors against novel attacks.
• Translate research findings into production detector specs and policy primitives with engineering.
• Publish internal and external write-ups on notable findings to build Obiguard’s research standing.
• Map attack classes and detectors to compliance frameworks (NIST AI RMF, ISO 42001, EU AI Act).
• Advise customers on risks during pilots and security reviews.

Connaissances

ML/NLP expertise

Adversarial ML

Python

Communication

Outils

LangGraph

AutoGen

MCP tooling

Description du poste

Careers / AI Safety Researcher

RESEARCHKuala Lumpur

Location

• Remote within KL, onsite when needed
• Kuala Lumpur

Contract type

• Full-time
• Open to part-time arrangements, and we welcome internship applications for this role.

AI Safety Researcher

Study emerging attack vectors against LLMs and agents. Turn research findings into production detectors and policy primitives.

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).

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.

Deep‑tech AI security and governance for organizations shipping LLMs in production. Engineered in Malaysia by veterans of security, identity, and ML platform.

Governance AIObichatSOCFlow

Platform

InspectionPolicyAllow‑listsAudit ledgerEvaluationsEthics & biasFramework mappingAll capabilities

By Role

• For Security Teams
• For Risk & Compliance
• For Platform Teams
• For Agent Teams

Resources

• Models
• Docs
• News
• Architecture
• Our Security

Company

AboutTeamCareersPartnersPressContact

Industries

Health Tech & MedTech FinTech & Financial Services Startups & Scale-ups Enterprise & SaaS Public Sector & Government Legal & Professional Services

Use Cases

Prompt Injection & Jailbreak Defense PII & Payment Data Redaction Shadow AI Discovery Secure Employee AI Chat Agentic AI Governance Regulatory Compliance & Audit Readiness Vulnerability & CVE Management Alert Response & Remediation

© 2026 OBIGUARD SDN. BHD.

• A Malaysia Digital (MD) Status Company

PrivacyTerms