AI Engineer – Agentic AI, Cloud Discovery

This is a fully remote position, open to applicants in India.

📋 Description

• Create and develop analysis and classification pipelines powered by LLM, subsequently deploying them as Go services.

• Experiment with various methods in Python, encompassing prompting techniques, RAG, structured data extraction, and ML classifiers.

• Deliver solutions that fulfill predetermined accuracy benchmarks.

• Establish ground-truth datasets, evaluation metrics, and regression testing suites to consistently assess and enhance model performance.

• Oversee model performance and drift in production, constructing processes to detect and rectify any decline in quality.

• Collaborate with security researchers to convert attack patterns and risk indicators into detection and summarization frameworks.

• Integrate AI-driven features with event, storage, and UI components to present actionable insights to security teams.

• Employ AI-assisted development methodologies to expedite implementation, testing, debugging, and experimentation.

• Engage in interviews regarding real-world applications of AI in software development, validation of AI outputs, and modifications to workflows.

⛳️ Requirements

• A minimum of 4 years in software engineering, with at least 2 years of experience delivering LLM- or ML-driven features to production.

• Proficient in Go for developing production backend services.

• Strong proficiency in Python for experimentation and data pipeline development.

• Practical experience with LLM APIs, prompt engineering, structured outputs, and RAG.

• Background in evaluating LLM/ML systems through offline assessments, human reviews, regression testing, or similar methods.

• Knowledge of AI agent architectures, including tool invocation, MCP or comparable protocols, multi-step planning, and common failure modes.

• Experience with cloud-native deployments utilizing Docker, Kubernetes, and AWS, GCP, or Azure.

• Fluent in English with excellent written and verbal communication abilities.

• Proficient with contemporary AI coding tools like Claude Code, Cursor, GitHub Copilot, Codex, or similar; this is essential.

• Strong sense of ownership and the capability to work autonomously in a remote-first, distributed setting.

• Preferred: Experience in security analytics, SIEM/SOAR, or digital forensics.

• Preferred: Familiarity with major cloud provider APIs, IAM frameworks, and resource inventory.

• Preferred: Knowledge of vector databases, embedding pipelines, or model fine-tuning.

• Preferred: Understanding of tracing AI applications and observability tools like OpenTelemetry.

• Preferred: Previous experience in cybersecurity, security tools, or trust & safety.

• Preferred: Experience in implementing AI-assisted or agentic development workflows across engineering teams.

🏝️ Benefits

• Contribute to a groundbreaking product at the convergence of cybersecurity and agentic AI.

• Transform innovative LLM/ML methodologies into production systems that safeguard enterprise clients.

• Engage in both AI experimentation and production engineering, spanning from Python prototypes to Go services.

• Assume responsibility for a significant workstream and shape architecture from the outset.

• Collaborate with a highly skilled, distributed team where AI is integral to the development process.

• Enjoy a remote-first working arrangement.