Staff AI Engineer - Production AI Platform Lead

Cobalt; Oregon; Hybrid; USD 275,000 - 300,000; Full time

Benefits offered by this job

Equity plan

Medical insurance

Wellness stipend

WFH equipment stipend

Paid time off

Parental leave

401(k) or pension

Job summary

Cobalt is seeking a Staff AI Engineer to lead production agent systems and set the technical direction for design, evaluation, shipping, and operation. You will mentor engineers and help teams turn prototypes into dependable production systems across security and platform domains.

Your focus includes agent platform reliability, observability, cost-effective model choices, and safe, scalable tool integration.

Qualifications

• 8–10+ years software engineering with technical leadership.
• Hands-on experience building and operating LLM-based agents in production.
• Proven track record improving agent reliability and reducing failures.
• Strong knowledge of agent architectures including memory management.
• Experience with production observability and incident investigation.
• Security awareness in agent systems and data isolation.

Responsibilities

• Set technical direction for agent systems across teams and orchestrations.
• Design, build and operate shared foundations: evaluation frameworks, observability and model access controls.
• Establish evaluation practices for task completion, accuracy, security and cost.
• Make agent workflows resilient to tool failures, timeouts and costs.
• Collaborate with security and platform teams on safe execution and data isolation.
• Define engineering standards: CI evals, model/versioning and staged rollouts.
• Lead model selection and cost optimization across workloads.
• Partner on production readiness and reliability improvements with teams.
• Mentor engineers through reviews, talks and guidance.
• Turn business priorities into a technical roadmap with clear outcomes.

Skills

LLM-based agents

Production systems leadership

Agent architectures

Observability & incident response

Cost optimization

Security in AI systems

Distributed back-end systems

Cloud platforms

Mentoring engineers

Roadmapping & collaboration

Tools

APIs

MCP

CI/CD

Cloud providers

Job description

Cobalt is seeking a Staff AI Engineer to lead production agent systems and set the technical direction for design, evaluation, shipping, and operation. You will mentor engineers and help teams turn prototypes into dependable production systems across security and platform domains.

Your focus includes agent platform reliability, observability, cost-effective model choices, and safe, scalable tool integration.