Senior AI Agent Architect for Observability & DevOps

Teradata; Hartford (CT); Hybrid; USD 150,000 - 190,000; Full time

Job summary

Teradata is seeking a Senior AI Platform Engineer to design and deploy AI-native agentic workflows across the Teradata AI Platform. You will architect agents that reason, analyze, and act across telemetry, applications, and cloud infrastructure, elevating engineering productivity and MTTR.

You will work with distributed systems and OpenTelemetry/Prometheus stacks, applying LLM-driven patterns and guardrails to production workflows while collaborating with cross-functional teams to embed

Qualifications

• 8+ years of software engineering experience with AI/ML in production
• Experience building AI agents, LLM-driven systems, or autonomous workflows
• Strong Python (required) and at least one of Java or Go
• Experience with distributed systems, telemetry data, and observability
• Foundational AI skills: prompt engineering, model evaluation, agent orchestration
• Hands-on experience integrating LLMs into production workflows with guardrails and evaluation

Responsibilities

• Lead design and development of AI-native agentic workflows
• Architect and deploy AI-driven agents for observability and automation
• Integrate agentic workflows across telemetry pipelines, apps, and cloud infrastructure
• Develop tooling to accelerate development velocity and reduce MTTR
• Apply AI patterns to automate complex debugging and diagnostics
• Drive AI-native development practices across apps, tooling, and platform engineering
• Partner with engineering teams to embed automation into CI/CD and DevOps workflows
• Explore AI to enhance productivity and impact across the workforce

Skills

Python

Java or Go

LLM/AI systems

Distributed systems

Telemetry/observability

Prompt engineering

Communication

Tools

OpenTelemetry

Prometheus

LLMs in production

CI/CD tooling

Job description

Teradata is seeking a Senior AI Platform Engineer to design and deploy AI-native agentic workflows across the Teradata AI Platform. You will architect agents that reason, analyze, and act across telemetry, applications, and cloud infrastructure, elevating engineering productivity and MTTR.

You will work with distributed systems and OpenTelemetry/Prometheus stacks, applying LLM-driven patterns and guardrails to production workflows while collaborating with cross-functional teams to embed