Posted on: 22/04/2026
Description :
- Lead the architecture and deployment of AI/ML and LLM-based cybersecurity solutions
- Design and implement RAG (Retrieval-Augmented Generation) pipelines with vector databases
- Build and scale multi-agent orchestration systems using LangChain, LangGraph, and advanced agent frameworks
- Drive development of cloud-native AI applications on Microsoft Azure
- Lead integration of LLMs (Azure OpenAI, Gemini) into enterprise workflows
- Define and implement AI engineering best practices, frameworks, and reusable components
- Oversee distributed, API-driven architecture and system integrations
- Ensure performance optimization, cost efficiency, and scalability of AI systems
- Collaborate with cybersecurity, product, and engineering teams in Agile environments
- Mentor engineers, conduct design reviews, and provide technical leadership
- Implement CI/CD pipelines, monitoring, logging, and observability frameworks
- Ensure compliance with enterprise security, governance, and responsible AI standards
Required Skills & Experience :
- 1014 years of experience in software engineering, with 4+ years in AI/ML or LLM systems
Strong hands-on expertise in :
- LangChain, LangGraph (Agents, Tools, orchestration patterns)
- RAG architectures and vector databases (Azure AI Search, PGVector)
- Azure OpenAI, Gemini, and LLM integration strategies
- Proven experience building AI-powered applications in Azure cloud environments
- Expertise in prompt engineering, evaluation frameworks, and structured output validation
- Strong background in distributed systems, microservices, and RESTful APIs
- Experience with Docker, Kubernetes (preferred), and containerized deployments
- Hands-on experience with CI/CD tools (GitHub Actions or similar)
- Experience with NoSQL databases and scalable system design
- Strong understanding of observability, telemetry, and feature flag strategies
- Excellent leadership, communication, and stakeholder management skills
Preferred Qualifications :
- Experience designing multi-agent AI systems across distributed environments
- Knowledge of LLM performance tuning and cost optimization
- Experience building enterprise AI platforms or reusable frameworks
- Exposure to cybersecurity, insider threat detection, or trust systems
- Familiarity with AI governance, compliance, and responsible AI practices
Did you find something suspicious?