Senior AI Engineer

Role overview

Agentic AI and platform responsibilities

• Lead development of autonomous workflows, multi-agent systems, and enterprise AI orchestration.
• Define architecture patterns and best practices for agents and Model Context Protocol integrations.
• Architect vector stores, embedding pipelines, and retrieval systems.
• Design document parsing, processing, and metadata extraction for enterprise knowledge management.
• Define API standards and AI service integration patterns across the bank.

Cloud and technical leadership

• Lead AI cloud architecture on Azure and GCP, addressing scalability, security, and cost optimization.
• Design Kafka event-driven architectures for real-time AI and streaming.
• Establish model-serving, monitoring, and MLOps infrastructure standards on OpenShift/Kubernetes.
• Mentor AI engineers and lead design reviews, code reviews, and architecture discussions.
• Promote CI/CD, code management, testing, knowledge management, and documentation practices.

Stakeholder engagement and governance

• Translate business requirements into technical solutions with AI product owners and stakeholders.
• Communicate technical concepts and trade-offs to senior management and steering committees.
• Contribute to AI governance and compliance with data policies, ethical standards, and regulatory requirements.
• Define and maintain AI solution SLAs and implement monitoring and alerting.

AI and software engineering expertise

• Deep expertise in LLMs, embedding models, generative AI architectures, orchestration frameworks, and multi-agent systems.
• Expert knowledge of vector databases, RAG, and knowledge retrieval patterns.
• Strong background in TensorFlow or PyTorch and model deployment tools such as MLflow or TFX.
• Advanced Python proficiency and experience with LangChain, LlamaIndex, Semantic Kernel, or similar frameworks.
• Experience with API design, microservices, and event-driven architecture.
• Advanced SQL, including stored procedures, window functions, temporary tables, and recursive queries.
• Experience with GitHub/GitLab, CI/CD pipelines, and code management.

Cloud and data engineering expertise

• Expert-level experience with Azure and/or GCP and object storage such as S3, GCS, or ABS.
• Advanced knowledge of Kafka, Spark, and workflow orchestration such as Airflow or Apache NiFi.
• Expertise in Docker and Kubernetes/OpenShift.
• Experience with end-to-end ML lifecycle management, model monitoring, versioning, and MLOps.

Role scope