𝗧𝗵𝗶𝘀 𝗿𝗼𝗹𝗲 𝗶𝘀 𝗳𝗼𝗿 𝗼𝗻𝗲 𝗼𝗳 𝘁𝗵𝗲 𝗪𝗲𝗲𝗸𝗱𝗮𝘆'𝘀 𝗰𝗹𝗶𝗲𝗻𝘁𝘀

𝗦𝗮𝗹𝗮𝗿𝘆 𝗿𝗮𝗻𝗴𝗲: 𝗥𝘀 𝟯𝟬𝟬𝟬𝟬𝟬𝟬 - 𝗥𝘀 𝟵𝟱𝟬𝟬𝟬𝟬𝟬 (𝗶𝗲 𝗜𝗡𝗥 𝟯𝟬-𝟵𝟱 𝗟𝗣𝗔)

Experience: 2+ yrs

Location: Hyderabad, Telangana, India

As a ML Researcher, you will spearhead the development of advanced machine learning models with a keen focus on adversarial robustness and red teaming techniques. Your role will involve designing, executing, and evaluating red team exercises to uncover potential vulnerabilities in AI systems, ensuring high reliability and security for mission-critical applications. You will collaborate closely with cross-functional teams, translating findings into actionable improvements, and publishing research in leading conferences. Your expertise will drive innovation in proactive threat modeling and contribute to a culture of continuous learning and resilience.

Requirements

𝗞𝗲𝘆 𝗥𝗲𝘀𝗽𝗼𝗻𝘀𝗶𝗯𝗶𝗹𝗶𝘁𝗶𝗲𝘀

• Design and implement red team strategies for evaluating machine learning models.

• Conduct adversarial testing, probing for biases, backdoors, and data poisoning.

• Develop new algorithms to detect and mitigate adversarial attacks in real-time.

• Analyze failure modes and produce detailed technical reports for stakeholders.

• Collaborate with security, product, and engineering teams to integrate findings.

• Mentor junior researchers and interns on red teaming best practices.

• Stay abreast of emerging research and threat landscapes in AI security.

• Lead presentations at conferences, workshops, and internal knowledge sessions.

• Contribute to open-source solutions and community initiatives in AI safety.

• Mentor and review submitted papers for top-tier conferences and journals.

𝗪𝗵𝗮𝘁 𝗠𝗮𝗸𝗲𝘀 𝗬𝗼𝘂 𝗮 𝗚𝗿𝗲𝗮𝘁 𝗙𝗶𝘁

• 2+ years of experience in machine learning research, with a focus on security or red teaming.

• Proven track record of publishing in top ML or security conferences (e.g., NeurIPS, ICML, CCS).

• Strong programming skills in Python, PyTorch/TensorFlow, and experience with adversarial libraries.

• Deep understanding of model architectures, data pipelines, and attack surfaces.

• Experience designing robust evaluation frameworks and metrics for adversarial defenses.

• Demonstrated ability to translate complex technical findings into clear, actionable recommendations.

• Excellent communication skills, with a history of presenting research at conferences or webinars.

• Ability to work independently and collaboratively in a fast-paced research environment.

• Familiarity with industry-standard tools for threat modeling and vulnerability assessment.

• Passion for continuous learning and staying ahead of evolving AI threats.