{"id":984526,"url":"https://alion.io/job/alice-intern-for-ai-security-rl-gyms","title":"Intern for AI Security RL Gyms","company":{"id":54114,"name":"Alice","domain":"alice.io","url":"https://alion.io/company/alice","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Comeet","truth_index":null},"role":"Early Careers","role_family":"Early Careers","seniority":"intern","employment_type":"internship","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Hanoi, Vietnam"],"countries":["VN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":8500,"max_usd":16000,"period":"year","method":"global_role_cell_scaled_by_country","sample_n":829},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Docker","optional":false},{"name":"LLM Guardrails","optional":true},{"name":"Red Teaming","optional":true}],"status":"closed","first_seen_at":"2026-08-25T11:25:50Z","employer_posted_date":"2026-10-08","last_verified_at":"2026-11-11T12:30:00Z","board_verified":false,"closed_at":"2026-11-11T12:30:00Z","days_open":78,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":78},"description":"Description\nAlice builds adversarial evaluation infrastructure used by the world's leading AI labs to stress-test their most capable agents before deployment. We're hiring interns for our RL Gym environments: adversarial training grounds where AI agents face prompt injection, social engineering, and data exfiltration scenarios.\nThe Role: You design prompt injection scenarios in YAML, run them against frontier models, validate success rates, and submit passing tasks.\nThe Task\nYou build adversarial prompt injection tasks for Alice's RL Gym platform. Each task is a self-contained YAML scenario simulating a realistic AI agent deployment, testing whether the agent can be manipulated into violating its safety policies.\nWhat a task includes:\nAn agent persona with a system prompt, security policies, and a defined set of tools.\nA simulated environment (e-commerce site, messaging platform, enterprise app) with content the agent interacts with.\nAn adversarial payload embedded in the environment (in messages, product listings, tool responses, documents) that attempts to trick the agent into a policy violation.\nA benign user request that naturally leads the agent to encounter the payload.\nDeterministic evaluation criteria specifying exactly what constitutes success (agent resists) vs. failure (agent is compromised).\nRequirements\nWhat We're Looking For\nStrong problem-solving skills and curiosity about AI security.\nInterest in adversarial thinking and understanding how AI agents can be manipulated through prompt injection or other attack techniques.\nBasic understanding of prompt injection concepts (or willingness to learn).\nComfortable writing structured content in YAML or able to learn quickly.\nFamiliar with using the command line (CLI); experience with Docker is a plus but not required.\nDetail-oriented and able to follow technical guidelines consistently.\nGood command of English.\nBackground in Computer Science, Cybersecurity, AI, Software Engineering, or related fields is preferred.\nWhat We Offer\nHands-on experience working on one of the most cutting-edge AI safety and security projects.\nInternship Allowance.\nMentorship from experienced AI security and red teaming professionals.\nOpportunity to contribute to evaluation environments used by leading AI labs.\nIf you’re eager to learn, innovate, and grow in the field of data engineering, we’d love to hear from you. Apply today to be part of a team that values creativity and technical excellence! \nPlease note that only shortlisted candidates will be contacted.\nAbout Alice\nAlice is a trust, safety, and security company built for the AI era. We safeguard the communicative technologies people use to create, collaborate, and interact- whether with each other or with machines.\nIn a world where AI has fundamentally changed the nature of risk, Alice provides end-to-end coverage across the entire AI lifecycle. We support frontier model labs, enterprises, and UGC platforms with a comprehensive suite of solutions: from model hardening evaluations and pre-deployment red-teaming to runtime guardrails and ongoing drift detection.\nAlice is widely considered a global leader in online safety and AI security. We have some of the most forward-thinking and passionate minds in the world working to safeguard over 3 billion users across the largest AI and tech platforms.\nIf you're creative and driven to secure the future of AI, we want to hear from you!","description_format":"text","description_chars":3425,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[{"language":"English","level":"All levels","optional":false}]},"benefits":[],"hiring_locations":[{"name":"Vietnam","iso":"VN","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","LLM & Generative AI","Threat Intelligence","Foundation Models"],"lifecycle":[{"event":"open","at":"2026-09-16T23:09:19Z"},{"event":"close","at":"2026-11-11T12:30:00Z"}],"visa":[],"liveness":null,"pay":null,"html_url":"https://alion.io/job/alice-intern-for-ai-security-rl-gyms","json_url":"https://alion.io/job/alice-intern-for-ai-security-rl-gyms.json","meta":{"generated_at":"2026-11-16T07:12:36Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":10823,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-17T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":54114},"rest":"https://alion.io/mcp/rest/get_company?id=54114"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Falice-intern-for-ai-security-rl-gyms"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"free","price":{"credits":0,"usd":0},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Falice-intern-for-ai-security-rl-gyms"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Falice-intern-for-ai-security-rl-gyms"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/alice-intern-for-ai-security-rl-gyms\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Falice-intern-for-ai-security-rl-gyms"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":984526}},{"tool":"search_jobs","arguments":{"company":"alice.io","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":984526},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}