AI Engineer

Experience Level: Minimum 6+ years

• Must Have Generative AI RAG Python Basic of deployment Strong ML background
• The AIQRM Reviewer ensures AI solutions meet governance and regulatory standards by reviewing AIQRM and VV reports during the validation phase of the AI lifecycle Supervising

Key Responsibilities

• Review AIQRM reports for completeness accuracy and alignment with internal templates and regulatory expectations
• Validate risk tiering evaluation metrics and continuous monitoring plans
• Ensure compliance with AI Principles and frameworks like the EU AI Act and ISOIEC standards
• Provide clear actionable feedback to development teams and track resolution of issues
• Collaborate with model owners and sponsors to clarify findings and support remediation
• Participating in periodic checking based on model risk tier

Qualifications

• Experience in AIML lifecycle especially validation and monitoring
• Familiarity with AI governance risk frameworks and tools like AIRA
• Strong analytical and communication skills
• Preferred Knowledge of LLMspecific risks and internal AIQRM process

Agent Design Development

• Design and implement autonomous agents using frameworks like Langgraph or Semantic Kernal
• Develop agents capable of reasoning planning and executing tasks
• LLM Integration Prompt Engineering
• Integrate large language models LLMs such as Azure Open AI
• Design and optimize prompts for task specific performance and reliability
• Tool API Integration
• Enable agents to interact with external tools APIs databases and services to perform complex operations
• Build custom tools and wrappers for agent use
• Memory Context Management
• Implement memory systems short-term long-term using vector databases like Mongo DB Elastic Search
• Design retrieval augmented generation RAG pipelines for contextual awareness
• Multiagent Collaboration
• Develop systems where multiple agents collaborate delegate tasks and communicate effectively
• Implement agent orchestration role assignment and coordination strategies
• Monitoring Evaluation Optimization
• Continuously monitor agent performance accuracy and reliability
• Documentation Collaboration
• Maintain clear documentation of agent design workflows and APIs
• Collaborate with other engineers to align AI capabilities with business goals

Required Skills

• Technical Expertise
• Strong proficiency in Python and experience with AIML libraries
• Deep understanding of LLMs their capabilities, limitations and finetuning techniques
• Agent Frameworks Architectures
• Handson experience with agent frameworks like Langgraph or Semantic Kernal
• Familiarity with agent planning tool usage and memory management
• Experience with Agents performance metrics collection
• Experience with Agents Monitoring
• Additional knowledge in MCP A2A protocols
• Prompt Engineering RAG
• Experience crafting effective prompts and building retrieval augmented generation pipelines
• Knowledge of embedding models and vector search techniques
• System Integration
• Experience integrating agents with RESTful APIs databases cloud services and third-party tools
• Familiarity with containerization Docker orchestration Kubernetes and CICD pipelines
• Cloud Deployment
• Experience deploying AI solutions on Azure cloud platforms
• Understanding of scalable architecture and performance optimization
• Good to have Asp Net 8 C Entity Framework Azure Services React SQL AKS Docker etc.