TAO Digital - Senior AI Platform Engineer

Job Summary :

We are seeking an experienced Senior AI Platform Engineer to drive the evolution and productionization of an existing LangGraph-based agentic SDLC framework. The role involves building scalable, enterprise-grade AI engineering capabilities with a strong focus on AWS, observability, security integration, workflow automation, and developer experience. The ideal candidate should possess deep expertise in agentic development, LangGraph, AWS, and software engineering practices, along with the ability to collaborate effectively across geographically distributed teams.

Key Responsibilities :

- Establish agentic framework standards, guardrails, and ways of working documentation.

- Design and enhance agentic workflows to support scalable and maintainable development practices.

- Implement inter-agent communication layers in remote and managed environments.

- Drive developer experience improvements by enabling clean setup processes with minimal or no manual configuration.

- Manage remote hosting and deployment on AWS.

- Support infrastructure provisioning and configuration using Terraform.

- Enable scalable and reliable deployment pipelines and operational processes.

- Build centralized telemetry, audit logging, and observability capabilities using OpenTelemetry.

- Integrate with telemetry tools and establish end-to-end monitoring mechanisms.

- Develop pipelines for centralized monitoring dashboards.

- Implement cost controls and usage monitoring mechanisms at engineer and team levels.

- Integrate SAST capabilities through Snyk within agent workflows.

- Support DAST agent workflows in collaboration with the Security team.

- Drive engineering workflow automation based on prioritized backlogs.

- Implement agent-driven, context-aware pull request review automation.

- Support CI/CD processes using GitHub Actions or equivalent tools.

- Contribute to prompt engineering activities to improve agent effectiveness and reliability.

- Promote software engineering best practices across various use cases and environments.

- Work effectively with globally distributed teams across multiple time zones.

- Collaborate with engineering, security, and platform teams to ensure seamless delivery and operational excellence.

- Communicate technical concepts clearly and effectively to stakeholders.