AI Engineer

Chabre IT Services is a global professional IT services provider, building long-lasting relationships with Enterprises. They specialize in tailor-made solutions, smart outsourcing, try&hire, and success fee services.

• Minimum 5 years of professional software engineering experience with strong backend expertise (Python preferred)
• Solid understanding of GenAI concepts, including LLM APIs, prompt engineering, RAG, tool/function calling, and agent orchestration
• Hands-on experience building production-grade LLM applications with focus on reliability, security, and observability
• Practical experience with frameworks such as LangChain, LangGraph, Semantic Kernel, or similar
• Strong knowledge of LLM evaluation techniques, hallucination mitigation, and guardrail implementation
• Experience integrating AI services (e.g., Azure OpenAI or similar) with attention to timeouts, fallback mechanisms, and safe outputs
• Background in distributed systems and scalable architectures (concurrency, async I/O, caching, API-driven design)
• Experience designing microservices, serverless solutions, or containerized applications
• Strong knowledge of cloud platforms (preferably Azure) and AI-related services
• Familiarity with vector databases and search technologies (e.g., Azure AI Search)
• Solid understanding of CI/CD pipelines and infrastructure automation
• Proficiency with Git-based version control and collaborative development workflows
• Experience implementing logging, tracing, monitoring, and metrics for production systems
• Understanding of IAM, authentication/authorization patterns (JWT/OAuth), and secure secret management
• Experience building automated testing frameworks, including evaluation harnesses for AI solutions
• Excellent communication skills and the ability to collaborate with both technical and non-technical stakeholders
• Strong problem-solving mindset and ownership attitude

• Design, develop, and operate AI-powered services integrating orchestration tools, workflows, and cloud infrastructure
• Build and maintain Retrieval-Augmented Generation (RAG) pipelines for processing internal knowledge, including ingestion, indexing, and evaluation
• Integrate AI-driven workflows into existing enterprise platforms and backend systems
• Define and implement tool/function schemas, orchestration patterns, and prompt strategies, ensuring high-quality and secure outputs
• Develop multi-agent and agentic workflows leveraging frameworks such as LangGraph or LangChain
• Automate testing, evaluation, and monitoring of AI systems, including quality validation and observability mechanisms
• Contribute to architectural decisions and promote engineering best practices across the SDLC
• Participate in Agile ceremonies and collaborate closely with cross-functional teams
• Mentor team members, foster alignment on technical direction, and raise the overall engineering standard
• Ensure responsible AI usage by applying governance, security, and compliance principles