GenAI Engineer

Job description

About The Role

• We are seeking a skilled GenAI Engineer to manage and maintain the infrastructure for our AI-powered chatbot and AI agent solutions. This role is primarily focused on provisioning, monitoring, and maintaining chatbot applications while also building new AI agent workflows and making incremental improvements to existing models. The ideal candidate will have a strong background in cloud infrastructure, MLOps, DevOps, and AI model lifecycle management, ensuring our chatbot and AI solutions remain stable, scalable, and efficient.

What You'll Do

• Infrastructure & Provisioning
• Deploy, manage, and optimize cloud-based AI/ML infrastructure (AWS, Azure, GCP, or on-prem).
• Automate infrastructure provisioning using IaC tools (Terraform, CloudFormation, etc.).
• Ensure scalability, security, and compliance of AI chatbot and agent deployments.
• Maintenance & Monitoring
• Monitor AI chatbot and agent workflows for performance, latency, and system health using observability tools.
• Identify and resolve issues related to AI models, APIs, and integrations.
• Ensure high availability, reliability, and optimal response times for chatbot services.
• AI Chatbot & AI Agent Workflow Development
• Design and build conversational AI chatbots and AI agent workflows tailored for business needs.
• Develop and integrate AI agent pipelines for task automation and intelligent decision-making.
• Work with LLMs, vector databases, and retrieval-augmented generation (RAG) techniques.
• Integrate chatbots with APIs, CRMs, databases, and third-party applications.
• Incremental Improvements
• Perform minor updates to chatbot models and configurations to enhance performance.
• Fine-tune existing AI models based on user feedback and operational data.
• Collaborate with stakeholders to apply incremental updates without disrupting production.
• Security & Compliance
• Implement best practices for AI model security, including API authentication and access control.
• Maintain compliance with data privacy regulations.
• Ensure AI models and chatbot interactions follow ethical AI guidelines.

Experience You'll Need

• 3+ years of experience in AI/ML infrastructure management, chatbot development, or MLOps.
• Hands-on experience with cloud platforms (AWS/GCP/Azure) and AI model deployment.
• Proficiency in Kubernetes, Docker, and CI/CD pipelines for AI model updates.
• Experience with monitoring and logging tools.
• Strong scripting skills (Python, Bash, Terraform, etc.).
• Experience in developing AI chatbots or agent workflows using LangChain, Rasa, OpenAI APIs, or similar frameworks.
• Working knowledge of vector databases.

Preferred Qualifications

• Experience with MLOps pipelines
• Understanding of AI governance, risk management, and responsible AI practices.
• Experience with multi-agent orchestration frameworks