Hiring for a AI Security Researcher for one of our clients

Company:A leading product startup in AI Security Space (one of our Clients)
Position: AI Security Researcher
Experience: 1-5 years
Location: Bengaluru, India - Onsite
Job ID: TOT2025101

---

Company Overview

We are an early-stage startup operating at the intersection of artificial intelligence and security. Our mission is to help organizations build and deploy AI applications with confidence and safety. The team is small, driven, and committed to solving real-world problems with technical depth and practical impact. We’re backed by credible investors and are focused on building foundational systems in a fast-growing and critical space. We’re backed by top VCs.

---

Role Overview

We need an offensive security engineer who thinks like an attacker first. Someone who sees a new AI agent and immediately starts plotting attack vectors. You'll advance our core technology for AI red teaming and adaptive guardrails while working on the cutting edge of agentic AI and MCP integrations.

• Develop novel attack techniques against LLMs, AI agents, and GenAI applications 
• Build automated red teaming tools that evolve with emerging threats 
• Research AI-specific vulnerabilities like prompt injections, jailbreaks, and agent manipulation 
• Create proof-of-concept exploits for enterprise AI deployments 
• Contribute to our open-source security research and tools

---

What We Want

The Hacker DNA: 

• Strong CTF background or bug bounty experience 
• Proven offensive security skills and penetration testing experience
• Natural instinct to break systems and find edge cases 
• Track record of vulnerability research or security tool development

Technical Foundation: 

• Solid programming skills (Python preferred) 
• Understanding of web security, API security, and modern attack vectors 
• Comfortable with Linux environments and automation 

AI Curiosity: (We'll help you level up here) 

• Interest in LLMs, prompt engineering, and AI applications 
• Curiosity about AI-specific attack surfaces 
• Bonus: Experience with prompt injections, model manipulation, or AI jailbreaking

Your New Team

 Here's what makes this opportunity special: 

• You'll be working alongside the world's best offensive security researchers. 
• Our team comes from top CTF teams globally and has repeatedly proven themselves against industry incumbents. 
• We've built careers breaking into the world's most secure systems. Now we're applying that same expertise to secure the AI revolution. 
• You'll learn from and collaborate with researchers who've found critical vulnerabilities, published groundbreaking research, and shaped how the industry thinks about AI security.

---

Why Join Us

• Ground floor at a rocket ship: Well-funded seed stage with massive market opportunity
• Work on unsolved problems: AI security challenges that don't have textbook answers yet
• Learn from the best: Team of world-class offensive security researchers
• Real impact: Protect enterprises from evolving AI threats at scale
• Cutting-edge tech: Access to latest AI models and enterprise systems

Other details

• Compensation:
  
  
  • Competitive base salary (we're not playing games here)
  • Equity (ESOPS) that actually means something (early-stage startup)
  • The freedom to experiment without 12 layers of approval  
   
• FAQs

  Q: Is this a remote position? A: No, this is an in-person role based in our HSR Layout, Bengaluru, India office.

  Q: Is this a full-time position? A: Yes, this is a full-time role. Growing a startup requires dedication!

To apply, please fill the form below. (For better experience, use laptop and Chrome browser)