AI Red Team Engineer

4 days ago


Delhi NCR, India Codefeast Full time ₹ 20,00,000 - ₹ 25,00,000 per year

Role Overview:

Lead offensive security testing of an AI Agenta tool-augmented LLM that can browse, run code, access connectors (GDrive, Gmail, GitHub, etc.), and act on behalf of users. Target is to uncover high-risk model mistakes, prompt-injection pathways, and data-exfiltration vectors before adversaries do.

What does day-to-day look like:

  • Design & automate multi-turn attack chains spanning browser, terminal, and connector-API misuse.
  • Craft multi-turn conversations that co-opt Agent tools (browser, terminal, connectors) to cause high-impact mistakes (unauthorized purchases, data deletion).
  • Design prompt-injection & data-exfiltration scenarios: malicious webpages, poisoned Google Docs, cross-connector inference attacks.
  • Script repeatable tests in Python or bash inside the VM; build harnesses to replay payloads after mitigations.
  • Verify compliance with policy guardrails (PD5, FA2) and attempt policy-bypass exploits.

Requirements:

  • 3+ yrs hands-on offensive security or adversarial ML experience, including at least 1 yr on LLM or prompt-injection testing.
  • Deep fluency with both classic AppSec techniques (XSS, CSRF, SSRF) and LLM-specific issues (jailbreaks, hidden prompt channels).
  • Comfortable orchestrating attacks that chain browser automation, terminal commands, HTTP requests, and API calls.
  • Solid Python/bash; can prototype tooling inside a constrained VM.
  • Track record of clear vulnerability write-ups (CVE, HackerOne, or internal bug bounty).
  • Working knowledge of privacy & financial-risk policies (GDPR, SOC2, or comparable).

Nice-to-Have

  • Published research or conference talks on AI red-teaming (DEF CON, Black Hat, MLSecOps, etc.).
  • Familiarity with OpenAI policy taxonomy (PD1-PD5, FA1-FA3).
  • Certifications: OSCP, GXPN, or CCSK (cloud).


  • NCR, India Codefeast Full time

    Role Overview: Lead offensive security testing of an AI Agenta tool-augmented LLM that can browse, run code, access connectors (GDrive, Gmail, GitHub, etc.), and act on behalf of users. Target is to uncover high-risk model mistakes, prompt-injection pathways, and data-exfiltration vectors before adversaries do. What does day-to-day look like: Design &...


  • Delhi, Delhi, India Innodata Inc. Full time

    Apply urgently if you are interested in Work from Office for 1 month (Contractual) in Bengaluru. We need Writers who have background in Generative AI and have experience working on LLM (Large Language Model).If you are interested, kindly complete the LLM Evaluation assessment (link below).LLM Evaluation Assessment Link:Assessment Guidelines:Please follow...


  • Delhi, India Innodata Inc. Full time € 15,600

    Apply urgently if you are interested in Work from Office for 1 month (Contractual) in Bengaluru. We need Writers who have background in Generative AI and have experience working on LLM (Large Language Model).If you are interested, kindly complete the LLM Evaluation assessment (link below).LLM Evaluation Assessment Link: Assessment Guidelines:Please follow...


  • Delhi, India Innodata Inc. Full time € 15,600

    Apply urgently if you are interested in Work from Office for 1 month (Contractual) in Bengaluru. We need Writers who have background in Generative AI and have experience working on LLM (Large Language Model).If you are interested, kindly complete the LLM Evaluation assessment (link below).- LLM Evaluation Assessment Link: LLM Assessment Guidelines: Please...

  • Red Team Operator

    1 week ago


    Delhi, Delhi, India VAYAM TECHNOLOGIES Full time

    About the role :A seasoned and technically elite Red Team Operator with a focus on network penetration testing, Command and Control (C2) infrastructure, and advanced post-exploitation tactics. This individual will be at the frontlines of simulating sophisticated threat actors to test, bypass, and break enterprise defenses. Key Responsibilities :- Plan and...


  • Delhi, Delhi, India GoDaddy Full time

    R019705 - New Delhi, Delhi, India - Engineering - Regular **Location Details**:India, Remote At GoDaddy the future of work looks different for each team. Some teams work in the office full-time; others have a hybrid arrangement (they work remotely some days and in the office some days) and some work entirely remotely. This is a remote position, so...


  • Delhi, Delhi, India r3 Consultant Full time

    We are looking for an experienced Red Team Security Assurance Analyst to join our Cyber Resilience & Defence team. In this role, you will lead offensive security operations, conduct simulated cyber-attacks, and support security assurance activities. You will apply industry frameworks like MITRE ATT&CK, leverage Cyber Threat Intelligence (CTI), perform Threat...


  • Delhi, India HackElite Pvt Ltd Full time

    About Us:-HackElite is a leading provider of comprehensive cybersecurity solutions. From advanced threat intelligence and vulnerability management to dark web monitoring and risk assessment, we specialize in helping businesses stay ahead of cyber threats. Backed by a team of seasoned experts, innovative tools, and a commitment to excellence, we empower...

  • AI Engineer

    4 weeks ago


    Delhi, Delhi, India Darwix AI Full time

    Job descriptionJob Title: AI EngineerCompany : Darwix AILocation : Gurgaon (On-site)Type : Full-TimeExperience : 2-6 YearsLevel : Senior LevelAbout Darwix AIDarwix AI is one of India's fastest-growing GenAI startups, revolutionizing the future of enterprise sales and customer engagement with real-time conversational intelligence. We are building a...

  • AI Engineer

    4 weeks ago


    Delhi, Delhi, India Darwix AI Full time

    Job descriptionJob Title: AI EngineerCompany : Darwix AILocation : Gurgaon (On-site)Type : Full-TimeExperience : 2-6 YearsLevel : Senior LevelAbout Darwix AIDarwix AI is one of India's fastest-growing GenAI startups, revolutionizing the future of enterprise sales and customer engagement with real-time conversational intelligence. We are building a...