Training Trains logo

AI Red Teaming Internship

Test AI systems the way attackers would, ethically and in your own lab: prompt injection, jailbreak categories, data leakage, bias, guardrails and professional reports.

PythonOllama / LLM APIsgarak / PyRIT / promptfooOWASP LLM Top 10

What you'll work on

Full syllabus: all 60 graded tasks

These are the actual tasks the internship portal assigns for this domain. You submit each one with proof (a GitHub link or document) and a mentor reviews it.

Level 1: Foundations (24 tasks)
  1. What AI red teaming is. Explain AI red teaming, why it matters, and the rules of ethical testing: only test systems you own or are permitted to test.
  2. How LLMs work. Explain tokens, prompts, system prompts, context windows and why models can be manipulated.
  3. Threat landscape. Summarise the OWASP Top 10 for LLM Applications with one example per risk.
  4. Set up a safe lab. Set up a local test app with a small open model (Ollama) or a sandboxed API key, in a repo named ai-redteam-internship.
  5. Testing plan. Write a test plan: scope, target behaviours, success criteria and what is out of bounds.
  6. Prompt injection basics. Build a small summariser app and show how instructions hidden in input text can change its behaviour.
  7. System prompt leakage. Test whether your own app reveals its system prompt and record the prompts that worked.
  8. Jailbreak categories. Classify jailbreak styles (role play, obfuscation, multi-turn) without publishing harmful outputs.
  9. Hallucination testing. Write 20 factual questions with known answers and measure how often the model is wrong or makes things up.
  10. Bias probing. Test the model with paired prompts that differ only in gender, caste or religion and compare the answers.
  11. Logging findings. Create a findings template: ID, prompt, response, severity, reproducibility and fix.
  12. Responsible disclosure. Explain responsible disclosure and how to report a model issue to a vendor's bug bounty or safety team.
  13. AI incident database. Read 10 real AI incidents from a public incident database and classify the failure types.
  14. Harm taxonomy. Build a taxonomy of AI harms (misinformation, privacy, bias, unsafe advice) with examples.
  15. Content policy reading. Summarise the usage policy of two AI providers and list what is not allowed.
  16. Prompt hygiene. Review five system prompts for secrets, weak instructions and missing rules.
  17. Refusal quality. Test how a model refuses harmful requests and rate whether refusals are helpful and polite.
  18. Over-refusal testing. Find safe requests that a model wrongly refuses and report them.
  19. Factuality test set. Build a set of 30 questions about Indian facts with verified answers and test a model.
  20. Citation checking. Check whether a model's cited sources actually exist and support its claims.
  21. Personal data handling. Test whether a chatbot asks for or stores personal data unnecessarily.
  22. Report writing practice. Rewrite three vague findings into clear, reproducible reports.
  23. Safe lab hygiene. Document how you isolate lab models, keys and logs from personal accounts.
  24. Threat actor profiles. Write profiles of likely misuse actors for an education chatbot.
Level 2: Building real features (20 tasks)
  1. Indirect prompt injection. Build a RAG demo where a planted document tries to hijack the answer, and show it working on your own app.
  2. Defences against injection. Add input separation, output checks and least-privilege tools to your app and retest.
  3. Tool and agent abuse. Build a small agent with one harmless tool and test whether injected text can make it misuse the tool.
  4. Data leakage. Test whether your RAG app leaks documents a user should not see, then add access filtering.
  5. Automated red teaming. Use an open-source tool (garak, PyRIT or promptfoo) to run an automated scan on your lab model.
  6. Evaluation suite. Build a repeatable test suite of attack prompts with pass/fail checks and run it in CI.
  7. Guardrails. Add a guardrail layer (moderation API, classifier or rules) and measure what it blocks and wrongly blocks.
  8. Multilingual attacks. Test whether safety behaviour changes when prompts are in Tamil, Hindi or mixed languages.
  9. Severity scoring. Define a severity scale for AI findings and score all your findings with it.
  10. Findings report. Write a professional red team report on your lab app with an executive summary and fixes.
  11. Encoding and obfuscation tests. Test whether filters can be bypassed with encodings or misspellings in your own lab app, and fix it.
  12. RAG poisoning. Plant a misleading document in your RAG lab and measure how often it changes answers.
  13. Agent tool permissions. Audit an agent's tools for dangerous capabilities and add confirmation steps.
  14. Output handling. Test whether model output can inject HTML or scripts into your web UI, and sanitise it.
  15. Rate and cost abuse. Test how an attacker could run up your API bill and add limits.
  16. Moderation benchmark. Compare two moderation tools on a labelled set and report precision and recall.
  17. Bias metrics. Measure response differences across groups with a simple metric and chart it.
  18. Image model testing. Test an image generation or vision model for unsafe or biased outputs in a controlled way.
  19. Red team playbook. Write a playbook with test categories, steps and severity rules for your team.
  20. Fix verification. Retest five fixed findings and confirm they stay fixed after a model update.
Level 3: Professional work and capstone (16 tasks)
  1. Multi-turn attack testing. Design multi-turn conversations that slowly push the model off-policy and measure when defences fail.
  2. Model supply chain. Review the risks of downloading third-party models and datasets (poisoning, unsafe pickles) and how to check them.
  3. Adversarial examples. Create adversarial inputs for a small image or text classifier and measure the accuracy drop.
  4. Privacy attacks concept. Explain membership inference and training-data extraction and how to reduce the risk.
  5. Red team exercise. Run a timed red team exercise on a teammate's AI app (with permission) and swap reports.
  6. Defence in depth design. Design layered defences for a production chatbot: input, model, output, tools, monitoring and human review.
  7. Monitoring for abuse. Add logging and alerting that flags likely attacks in production traffic.
  8. Capstone: AI security assessment. Deliver a full assessment of an AI app you built: threat model, automated and manual testing, fixes, retest results and a final report.
  9. Automated adversarial generation. Use one model to generate test attacks against another in your lab and filter the results.
  10. Long-context attacks. Test whether instructions buried deep in long documents affect your app.
  11. Multi-agent risks. Test how one agent's output can mislead another in a two-agent system.
  12. Evaluation in CI. Run your safety regression suite automatically on every prompt or model change.
  13. Governance mapping. Map your findings to the NIST AI Risk Management Framework categories.
  14. Responsible disclosure drill. Write a disclosure report for a finding as if submitting to a vendor's program.
  15. Executive briefing. Brief a non-technical audience on AI risks of your app in 5 minutes.
  16. Capstone 2: red team engagement. Run a full red team engagement on a teammate's AI product with rules of engagement, testing, report, fixes and retest results.

Real software work, not just training

Every AI Red Teaming task is reviewed by our team and saved to your portfolio. Interns who pass the readiness check can take real work from Training Trains, W3AppDevelopers and DomainHostly projects on the Company Work board.

Cyber SecurityAI / Machine Learning Solutions
See the software we build →

Frequently asked questions

Do I need experience to join the AI Red Teaming internship?+

Python basics and an interest in security. All testing is on your own lab apps or with written permission.

What will I do in the AI Red Teaming internship?+

You complete 60 graded tasks in three levels: foundations, real features, and professional work. Each task is submitted with GitHub or document proof and reviewed. The final capstone is: Capstone 2: red team engagement.

Do I get a certificate for the AI Red Teaming internship?+

Yes. After your required tasks are approved, your attendance is above 75% and you pass the proctored final exam, you get a graded completion certificate that anyone can verify at trainingtrains.com/verify.

Can I do the AI Red Teaming internship online?+

Yes. You can do it fully online from home, or offline at our Erode and Perundurai branches. Tasks, quizzes and mentor reviews are the same in both modes.

Available both online (work from home) and offline at our Erode and Perundurai branches - see the full internship program details for departments, duration, and the application process.

Apply for the AI Red Teaming internship