Senior AI Platform Engineer: Agent OS & Safe Workflows

Talanto; California, Northern (MO, KY); Hybrid; USD 168,000 - 270,000; Full time

Benefits offered by this job

Flextime and flexible time off

Comprehensive health and wellness

Career growth and leadership programs

Job summary

Talanto is seeking a senior software engineer to help build the Agent OS platform. You will design and implement core services, craft reliable APIs, and debug production issues to keep complex AI workflows running safely.

With 7+ years in production software, you will work across Python/Java/C#, cloud infrastructure, and modern AI tooling. This role is remote for US/Canada, with strong emphasis on reliability and platform-wide impact.

Qualifications

• 7+ years of production software engineering experience.
• Strong hands-on coding in Python, Java, or C#; Python preferred.
• Experience building AI/platform systems in production.
• Distributed systems, event-driven or async workflows experience.
• Experience with cloud infrastructure (Azure/AWS/GCP).

Responsibilities

• Design and implement core Agent OS platform services.
• Write production code and review implementation details.
• Build reliable APIs, workflows, tools, and services for agent execution.
• Inspect traces, debug failures, and improve production behavior.
• Design evaluation scenarios and regression suites for agent workflows.
• Partner with domain teams to turn use cases into reusable platform patterns.
• Define platform contracts for tools, actions, context, and memory.

Skills

Python

Java

C#

LangChain

Kubernetes

Docker

OpenAI

Cloud (Azure/AWS/GCP)

Education

B.S./M.S./PhD in CS or related field

Tools

Kubernetes

Docker

Azure

AWS

GCP

Job description

Talanto is seeking a senior software engineer to help build the Agent OS platform. You will design and implement core services, craft reliable APIs, and debug production issues to keep complex AI workflows running safely.

With 7+ years in production software, you will work across Python/Java/C#, cloud infrastructure, and modern AI tooling. This role is remote for US/Canada, with strong emphasis on reliability and platform-wide impact.