About the role#
You will join the team to red team real-world LLM deployments, design evaluation harnesses, and scale the Elloe output-level safety layer. This work involves forensic risk mapping rather than simple prompt tuning. You will work with product and safety leads to uncover failure patterns and codify guardrails for systems used by governments and enterprises.
What you'll do#
- Create prompts to trigger hallucinations, policy violations, or failure scenarios.
- Stress test Elloe-protected deployments using open and proprietary models.
- Document behavioral exploits across use cases such as healthcare, compliance, and government.
- Build truthsets and scoring rubrics tied to factuality, policy, or ethical standards.
- Benchmark Elloe modules across model types including Claude, GPT-4, and Gemini.
- Collaborate with product to refine and expand evaluation harnesses.
- Identify blind spots in current detection logic.
- Recommend scoring methods or red flag thresholds for deployment.
- Support internal model comparison reports or customer safety audits.
What you'll need#
- Background as an ML/AI researcher or engineer (undergrad, grad, or early career).
- Experience working with LLMs, evaluation sets, and prompt design.
- Strong attention to detail, grounded in safety and adversarial thinking.
- Bonus points for exposure to safety benchmarks like TruthfulQA, MMLU, or red teaming tools.
Location & details#
- This role is remote and open to global candidates.
- The position is a full-time, paid internship.
- The term is rolling with a duration of 12 to 16 weeks.
About Elloe AI | Immune System for AI
Elloe AI operates as a compliance layer for artificial intelligence. It provides safety tools for generative models used in regulated sectors like hospitals and government agencies. The company focuses on tracing and flagging model outputs to prevent errors. It is based in Austin, Texas, and maintains a staff of 11 to 50 employees.
How to get in at Elloe AI | Immune System for AI
Applying early gives you a distinct advantage at Elloe AI, as recruiters often review the first candidates before the application volume becomes unmanageable. Intern Insider sends an instant alert the moment a role matching your target is published anywhere, so you apply among the first. This helps you avoid the frustration of submitting your resume to a crowded, unseen pile. You can also improve your response rates by reaching out to the people actually hiring for the team. Intern Insider surfaces the recruiters behind the company roles so you can contact them directly to ask about the position or a referral. This direct approach often proves more effective than relying on standard application portals.
