- Agentic AI Generative AI Development
- Design and implement Agentic AI architectures including singleagent and multiagent systems
- Build LLMpowered workflows enabling reasoning planning tool invocation and task execution
- Develop AI agents using Pythonbased frameworks for orchestration memory and context management
- Implement RetrievalAugmented Generation RAG pipelines using structured and unstructured data sources
- Integrate large language models LLMs from cloud AI platforms into enterprise applications
- Engineering Integration
- Develop RESTful APIs and backend services to expose AI agent capabilities
- Integrate agents with enterprise tools APIs databases and automation workflows
- Collaborate with product and engineering teams to translate business problems into AIdriven solutions
- Ensure AI solutions follow securebydesign and responsible AI practices
- Data Pipelines MLOps
- Build and maintain data pipelines supporting training inference and RAG workflows
- Implement MLOps pipelines for model versioning deployment monitoring and retraining
- Apply observability logging and performance monitoring for AI systems in production
- Optimise model performance for cost latency reliability and scalability
- Cloud Deployment
- Deploy AI workloads on cloud platforms AWS Azure GCP using scalable architectures
- Work with containerisation and orchestration tools to support production AI deployments
- Ensure high availability fault tolerance and compliance in cloud environments
- Required Skill
- Primary Skills
- Agentic AI autonomous agents reasoning workflows toolcalling patterns
- Python development for AIML applications
- Generative AI and Large Language Models LLMs
- Secondary Skills
- Cloud Platforms AWS Azure or GCP
- Data Pipelines and Data Engineering concepts
- MLOps model deployment monitoring CICD for ML