Senior AI Security Engineer

Company We partner with enterprises toadvise, build, secure, and operationalize AI systems at scale . Our focus is on developingGenerative AI (GenAI), Agentic AI, and Reinforcement Learning-driven systems , while embeddingsecurity, governance, and risk controls directly into AI workflows . We enable organizations to safely deployLLMs, autonomous agents, and adaptive decisioning systemsin regulated, mission-critical environments.Job Description As aSenior AI Security Engineer (GenAI, Agentic AI & Reinforcement Learning) , you will lead the design and implementation ofsecure, scalable, and adaptive AI systems , includingLLM-based applications, agentic workflows, and RL-driven decision engines . This role goes beyond traditional security—you will buildintelligent, self-improving security review systemsusingagentic frameworks (LangGraph, LangChain, LangSmith)andreinforcement learning techniquesto continuously enhance AI risk evaluation, policy enforcement, and approval workflows. You will collaborate closely withAI/ML engineers, platform teams, and governance stakeholdersto embedautonomous, learning-based security mechanismsinto enterprise AI ecosystems.Key Responsibilities GenAI, Agentic AI & RL Security Architecture Design and secureLLM, RAG, multi-agent, and RL-driven systems Implement security controls for: Autonomous decision-making agents RL-based adaptive systems Tool-using and API-integrated agents Ensuresafe exploration and bounded behaviorin RL environmentsAgentic AI + Reinforcement Learning for Security Automation (Core Focus) Buildagentic AI pipelinesusing: LangGraph→ multi-step, stateful security workflows LangChain→ LLM orchestration and tool integration LangSmith→ observability, tracing, and evaluation DevelopRL-enhanced security agentsthat: Learn from past approval decisions Optimize risk scoring and classification over time Continuously improve policy enforcement accuracy Implementfeedback loops (human-in-the-loop + automated)to train: Risk evaluation agents Compliance validation agents Automateend-to-end intake → evaluation → approval pipelinesfor GenAI and Agentic AI use casesReinforcement Learning Implementation & Governance Design and implementRL models for adaptive security decisioning Policy optimization Risk-based prioritization Dynamic access control adjustments Applysafe RL techniques : Reward shaping aligned with compliance and security policies Constraint-based RL (safe exploration boundaries) Monitor and mitigate risks such as: Reward hacking Unsafe policy learning Drift in learned behaviors Integrate RL models intoAI governance workflowsfor continuous improvementAI Risk, Governance & Compliance Translate frameworks such as: NIST AI RMF EU AI Act OWASP Top 10 for LLMs intoautomated, adaptive controls Builddynamic risk scoring systemsenhanced by RL: Adversarial Risk Score Model Drift Index Policy Compliance Confidence Score Generatereal-time AI risk heat maps and approval recommendations Implementpolicy-as-code + policy-learning systemsSecurity Assessment & Red Teaming ConductAI/LLM/RL system security assessments Performred teaming across : Prompt injection scenarios Agent tool misuse RL policy exploitation Evaluate vulnerabilities in: RAG pipelines Multi-agent coordination RL training environmentsAI/ML Lifecycle & LLMOps/RLOps Security Secure the full lifecycle: Data ingestion, labeling, and validation Model training (LLM + RL) withGPU isolation and sandboxing Deployment, inference, and continuous learning loops ImplementRLOps + LLMOps security controls Ensure: Model lineage and provenance Secure feedback loops Version control for policies and learned behaviorsMonitoring, Incident Response & Observability BuildAI + RL-aware monitoring systems Detect anomalies in: LLM outputs Agent decisions RL policy shifts Developincident response playbooks for autonomous systems Createexecutive dashboards linking AI + RL risk to business KPIsData Security & Access Control Implementfine-grained and adaptive access controls Secure: RAG knowledge bases Vector databases RL training datasets Ensure compliance withdata privacy and residency requirementsThought Leadership Act as an SME in: AI Security Agentic AI systems Reinforcement Learning security Research emerging risks in: Autonomous AI systems Self-improving models Multi-agent + RL ecosystemsQualifications Required Bachelor’s degree in Computer Science, Engineering, or related field 3–5+ years of experience incybersecurity (application, cloud, or data security) Strong experience inautomation, scripting, and security tool development Hands-on experience with: GenAI / LLM applications AI threat modeling and risk assessment Deep understanding of AI threat vectors: Prompt injection Data leakage Adversarial attacks Experience withAzure or AWS cloud security ecosystemsPreferred (Strong Differentiators) GenAI & Agentic AI Hands-on experience with: LangChain LangGraph LangSmith Experience buildingagentic workflows and multi-agent systems Experience securingRAG pipelines and LLM applicationsReinforcement Learning (Highly Valued) Experience implementingReinforcement Learning models : Policy optimization Reward function design Decision-making systems Familiarity with: RLHF (Reinforcement Learning from Human Feedback) Safe RL and constrained optimization Experience integrating RL into: Automation workflows Security decision systems Understanding ofRLOps pipelines and lifecycle managementSecurity & Governance Familiarity with: OWASP Top 10 for LLMs NIST AI RMF, EU AI Act, ISO 42001 Experience with: Microsoft Sentinel, Azure Monitor, Purview, Key Vault Policy-as-code and automated compliance frameworks Knowledge ofdata privacy regulations (GDPR, DORA, etc.)

Apply Now