Principal Software Engineer
DigitalOcean2 months ago
Bengaluru, IndiaStaff+
Responsibilities
- Define how AI security controls are integrated into DigitalOcean’s customer-facing products.
- Build and deploy detection strategies, guardrails, security tooling, and automation with Security Data Science and Security Engineering.
- Implement and monitor online and batch inference endpoints for in-house AI/ML models, including drift detection and performance improvements.
- Lead AI red-team testing covering jailbreaks, prompt injection, evasion, poisoning, and model extraction.
- Lead security reviews and provide architectural sign-off and escalation guidance for major AI product initiatives.
- Threat model the full AI lifecycle, including data ingestion, training, fine-tuning, evaluation, serving, RAG, agent frameworks, and monitoring.
- Own the AI security strategy, multi-year roadmap, and AI Risk & Governance framework.
- Represent AI security in executive and board-level briefings and define positions on emerging AI security topics.
Requirements
- 15+ years of cybersecurity experience, including at least 4–5 years in AI/ML security, adversarial machine learning, or security data science in a production cloud or technology environment.
- Organizational experience defining and driving AI or security programs and owning strategy and roadmaps.
- Practitioner-level expertise in adversarial ML attacks and defenses, including evasion, poisoning, model extraction, membership inference, and prompt injection.
- Ability to evaluate AI security research and translate it into engineering guidance and organizational policy.
- Experience communicating technical risk to executives and senior leadership in business terms.
- Strong programming skills in Python and Go, including building security tooling and automation.
- Experience reviewing AI/ML architectures covering data ingestion, feature engineering, training pipelines, model serving, and continuous monitoring.
- Hands-on experience with AI red-team, defensive, and model supply-chain tooling.
- Bachelor’s or Master’s degree in Computer Science, Information Security, Mathematics, or a related field, or equivalent depth of practical experience.
- Fluency in OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF, ISO/IEC 42001, and the EU AI Act.
- Experience with a cloud provider, security product company, or large-scale internet platform operating AI/ML systems at customer-facing scale.
- Familiarity with production LLM security, including securing RAG pipelines, agentic frameworks, and model APIs against prompt injection, jailbreaking, and data exfiltration.
Benefits
- Reimbursement for relevant conferences, training, and education.
- Access to LinkedIn Learning’s 10,000+ courses.
- Employee Assistance Program, local employee meetups, and flexible time off.
- Bonus eligibility, equity compensation, equity grants upon hire, and an Employee Stock Purchase Program.
- Located in Bengaluru, India, with a hybrid work arrangement.
About DigitalOcean
DigitalOcean provides cloud infrastructure and platform services for developers, startups, and small to mid-sized businesses, including virtual machines (Droplets), managed Kubernetes and databases, object/block storage, networking, and GPUs for AI workloads. It operates a usage-based, self-service public cloud with APIs, CLI, and a marketplace to deploy and scale applications. Founded in 2012 and headquartered in Broomfield, Colorado, DigitalOcean is a public company listed on the NYSE.