Job Description

At CACTUS, we are currently hiring an AI QA & Safety Engineer based in Delhi. This is an on-site, full-time employment opportunity.

Job Responsibilities

Adversarial ML & Model Security Testing

- Design and execute adversarial attack campaigns against document intelligence, predictive analytics, fraud detection, computer vision, face recognition, and liveness detection systems
- Develop and maintain a reusable adversarial ML attack library and test harness for repeatable pre-production evaluation
- Produce adversarial-robustness reports for each pod service with quantitative measures, reproducible attack notebooks, and prioritised mitigation guidance

LLM, RAG & Agentic AI Red Teaming

- Lead structured red-team exercises against LLM, RAG and agentic AI deployments across the platform.
- Cover prompt injection, jailbreaks, indirect prompt injection via retrieved documents, data exfiltration, unsafe tool invocation, sandbox escape and policy-boundary violations by agents
- Develop and maintain red-team playbooks publish anonymised playbooks and evaluation sets under standard metadata
- Advise pods on guardrail selection, output filtering, RAG source-integrity controls, retrieval provenance, and agent policy design

Hallucination, Calibration & Responsible AI Evaluation

- Design and run hallucination measurement, groundedness checks, and calibration/uncertainty evaluation for RAG systems and generative outputs across teams
- Run bias and fairness audits using quantitative metrics - demographic parity, equalised odds, calibration, subgroup accuracy.
- Conduct explainability evaluation (SHAP, LIME, Captum) and lightweight privacy impact assessments on team deliverables
- Author the technical safety evaluation content in model cards, dataset sheets, bias/hallucination/safety evaluation reports.

AI Security Architecture & Threat Modelling

- Own AI-specific threat modelling end-to-end for all pod systems under development - STRIDE, MITRE ATT&CK;, MITRE ATLAS and OWASP Top 10 for LLMs - including data pipelines, retrieval sources, model artefacts, prompt paths, tool interfaces and output surfaces
- Contribute AI security and Responsible AI requirements to RDRs and procurement documents.

Cross-Functional Team Advisory and Upskilling

- Advise each team's AI QA Engineer on safety and Responsible AI test design, sample selection, evaluation metrics and evidence capture
- Brief and upskill teams on AI-specific security concerns and Responsible AI controls.

Research, Publication & Knowledge Transfer

- Track adversarial ML, LLM safety, agentic-AI safety and Responsible AI research literature translate relevant findings into team-usable checks, controls and evaluation additions




- Maintain the platform's open-source AI safety testing toolkit deposit reusable notebooks, evaluation harnesses and playbooks, and publish reusable evaluation sets and safety artefacts under standard metadata for re-use.

Qualifications and Prerequisites

Educational Qualification

- B.Tech./B.E. or M.Tech./M.S./M.Sc. in Computer Science, Information Security, AI/ML, or a related quantitative discipline (Must have)
- Advanced degree (M.Tech./M.S./Ph.D.) with a thesis or published work in adversarial ML, AI security, LLM safety, or Responsible AI is highly desirable
- Certifications (Desirable): OSCP, GWAPT or CEH combined with demonstrable AI/ML security work DeepLearning.AI or equivalent ML foundations MLSecOps or LLM security specialist certifications where available
- Non-traditional backgrounds with demonstrable adversarial ML research, published safety work, credible LLM red-team disclosures, or CTF/red-team achievements will be considered in lieu of formal qualification

Work Experience

- 6+ years total in ML, applied AI, security research, or a closely related discipline minimum 3 years specifically in adversarial ML, AI red teaming, LLM safety evaluation, or AI/ML security research
- Demonstrable hands-on LLM red-teaming experience with documented prompt injection, jailbreak, indirect-prompt-injection or agentic-tool-misuse campaigns against production or production-like systems
- Demonstrable adversarial ML work - evasion, model inversion, membership inference, model extraction, or data poisoning - against non-toy classifiers, vision models, or NLP systems
- Prior experience delivering safety, red-team, or Responsible AI work in BFSI, healthcare, or another regulated sector is a strong plus
- Prior experience advising or upskilling non-specialist engineering, security, or compliance teams on AI-specific security concerns is desirable

Technical Competencies

- Programming & ML Frameworks: Python (advanced) PyTorch or TensorFlow Hugging Face Transformers standard data-science tooling (NumPy, pandas, scikit-learn)
- Adversarial ML: Adversarial Robustness Toolbox (ART), Foolbox, CleverHans or equivalent ability to implement custom attacks and defences knowledge of certified robustness techniques
- LLM & Agentic AI Red Teaming: Demonstrable production-relevant experience with prompt injection, jailbreak,



indirect-prompt-injection, data-exfiltration, tool-misuse, sandbox-escape and multi-turn manipulation familiarity with LLM guardrail frameworks (NeMo Guardrails, Guardrails AI, Llama Guard) and open red-team datasets
- Hallucination, Calibration & RAG Evaluation: RAGAS or equivalent groundedness metrics, faithfulness scoring, retrieval quality metrics, calibration and uncertainty quantification ability to build custom evaluation harnesses for RAG and generative pipelines
- Threat Modelling & AI Security Frameworks: STRIDE, MITRE ATT&CK;, MITRE ATLAS, OWASP Top 10 for LLMs, OWASP ML Top 10 ability to translate threat models into control specifications and test cases
- Explainability & Fairness: SHAP, LIME, Captum for model explainability Fairlearn and AI Fairness 360 for fairness metrics ability to design subgroup-fairness protocols for identity verification, fraud and predictive models
- Privacy-Enhancing Techniques: Working awareness of differential privacy, federated learning, PII redaction and anonymisation techniques ability to run privacy impact assessments on model and data pipelines
- Communication & Advisory: Ability to author explicit technical safety reports for a mixed engineering, architecture and executive audience ability to brief and upskill non-AI security engineers and compliance colleagues ability to represent the platform across various working groups

Additional Information

If you are among the qualified candidates, one of our recruiters will contact you on phone or email with further details.

About CACTUS

Established in 2002, Cactus Communications (cactusglobal.com) is a leading technology company that specializes in expert services and AI-driven products which improve how research gets funded, published, communicated, and discovered. Its flagship brand Editage offers a comprehensive suite of researcher solutions, including expert services and cutting-edge AI products like Mind the Graph, Paperpal, and R Discovery. With offices in Princeton, London, Singapore, Beijing, Shanghai, Seoul, Tokyo, and Mumbai and a global workforce of over 3,000 experts, CACTUS is a pioneer in workplace best practices and has been consistently recognized as a great place to work.

Awards and Recognition

- Employers of the Future, 2024
- Excellence in Employer Branding (Gold), 2024
- ISO 17100 certification for translation services, 2024
- Future of Workplace Disruptor, 2023
- Top 100 Companies for Remote Jobs (Ranked #14), 2023
- Three-star Eruboshi certification, 2023
- India's Best Workplaces™ for Women (Top 100), 2022
- Quartz's Best Companies for Remote Workers, 2022
- HR Asia's Best Companies to Work for in Asia, 2021

📌 AI QA Engineer (India)
🏢 Cactus Global
📍 India