Evaluate how effectively static analysis tools detect vulnerabilities in GenAI applications. Build small, runnable agent and RAG codebases with realistic examples of Sensitive Information Disclosure and Excessive Agency, including fixed and near-miss versions. Trace, annotate, test, and explain each finding.
Responsibilities
Build runnable agent/RAG repositories with code-reachable Sensitive Information Disclosure or Excessive Agency vulnerabilities across tool calling, memory, and MCP.
Create vulnerable, fixed, and hard-negative variants with minimal security-relevant differences.
Trace and annotate assets, data/action paths, controls, root causes, severity, and residual risk.
Define authorization contexts and write deterministic tests to validate vulnerable, fixed, and negative behavior.
Recommend security controls and participate in calibration and peer review.
Qualifications
5+ years of experience in application/product security or security-focused software engineering, including secure code review.
Experience with source-to-sink analysis, taint analysis, SAST, CodeQL, or Semgrep.
Hands-on experience building LLM agents or RAG systems using frameworks such as LangChain, LlamaIndex, OpenAI/Anthropic SDKs, or MCP.
Strong authorization knowledge, including actors, trust boundaries, tenants, OAuth, IAM, identity, permitted data/actions, purposes, recipients, and document-level access control.
Production coding experience in Python and/or TypeScript, with strong judgment in distinguishing genuine SID/EA findings from non-findings.
Experience with OWASP LLM security risks, MCP, threat modeling, or security evaluation is a plus.
Assignment Details
Contract assignment; no medical or paid leave.
Full-time or part-time commitment: 40 or 20 hours per week, with 4 hours of PST overlap.
Engagement length: 4 weeks; start as soon as possible.
Rate: Up to $25/hour.
Positions: 70.
Locations: Bangladesh, Brazil, Colombia, Egypt, Ghana, India, Indonesia, Nigeria, Turkey, and the USA.
... Large Language Model (LLM) performance and fine-tuning strategies to ensure high accuracy and relevance for enterprise-grade applications.- Architect cloud-native AI infrastructure on AWS to ensure high availability, low latency, and cost-effective model deployment.- Mentor junior engineers and lead technical code reviews to ...
... do - Responsible for building and running the security controls that find and govern the use of artificial intelligence across Danaher, including chat tools, AI platforms - Configure, tune, and maintain security policies for the AI control plane in CrowdStrike Falcon AI Detection and Response (now Falcon Guardian) and ...
Danaher seeks a Senior Engineer to design and operationalize AI security controls across the organization. The role involves configuring CrowdStrike Falcon policies, managing AI gateways, building detections aligned to OWASP LLM standards, and automating security workflows using Python and PowerShell. Responsibilities - ...
AI Platform Engineer - Job DescriptionExperience : 4 - 8 YearsLocation : Gurgaon/NoidaEmployment Type : Full-timeRole Overview : We are looking for a highly skilled AI Platform Engineer with 4 - 6 years of experience in building AI driven applications using Large Language Models (LLMs) and modern AI frameworks. The ideal ...
Role : AI Engineer (Agentic AI & LLM Solutions).Team : CDC AI https://jobeax.com/link/rHvnCLDqY8LVhp2v : Cloud and Data https://jobeax.com/link/LglGQXnMPM3YTPQ6 of the Role : The AI Engineer designs, builds, tests, and operates AI and Agentic AI solutions in support of the CDC AI Transformation https://jobeax.com/link/UJbmKUwLFenkn31S ...
Role : AI Engineer (Agentic AI & LLM Solutions).Team : CDC AI https://jobeax.com/link/rHvnCLDqY8LVhp2v : Cloud and Data https://jobeax.com/link/LglGQXnMPM3YTPQ6 of the Role : The AI Engineer designs, builds, tests, and operates AI and Agentic AI solutions in support of the CDC AI Transformation https://jobeax.com/link/UJbmKUwLFenkn31S ...
... AI-assisted technologies within cybersecurity or security operations. - Understanding of AI/LLM security risks and how AI technologies can affect enterprise security. - Experience applying AI to areas such as anomaly detection, security monitoring, incident investigation, vulnerability management, or security automation. ...
... for prompts, tool selection, and retrieval quality.- Improve retrieval and context assembly using measured failures.- Partner with Data Platform and product engineers, clinical/data SMEs, DME/QA, and security https://jobeax.com/link/tbV87hPFdlI3znrY : - 5+ years in software/AI engineering, including production LLM applications ...
... solutions, including LLM-powered applications, Retrieval-Augmented Generation (RAG), and agentic https://jobeax.com/link/KolRTDQZdfDk7db0 role involves integrating AI capabilities with enterprise data and systems to build reliable, scalable, and secure GenAI applications. The candidate will work closely with senior engineers ...
... performance bottlenecks in LLM applications and retrieval pipelines.- Design robust architectures capable of supporting enterprise workloads.- Implement appropriate security controls and production AI best practices.6. Technical Leadership : - Provide technical direction and mentorship to engineering teams.- Conduct architecture ...