AI Product Engineer - LLMs, Agents & Workflow Automation

Cohere; New York (NY); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

Weekly Lunch Stipend

Health Benefits

Dental Benefits

Mental Health Budget

RRSP Matching

401K

Pension Scheme

Parental Leave Top-up

Arts & Culture Benefit

Fitness/Wellness Benefit

Quality Time Benefit

Workspace Improvement Credit

Education & Learning Stipend

Paid Vacation

Travel Budget

Company Offsite

Co-working Benefit

Home Office Stipend

Job summary

Cohere is building AI-powered product experiences and agentic workflows in the North platform. You will ship LLM-based features, improve observability, and implement evaluation feedback loops to ensure reliability in enterprise contexts.

We seek a strong software engineer with a proven track record of production-grade AI systems, capable of debugging complex AI failures and delivering high-quality product design insights.

Qualifications

• Proven track record of shipping LLM or agent-powered products into production.
• Ability to debug complex real-world AI failures.
• Strong product taste and design sensibilities.

Responsibilities

• Build and optimize AI-powered product experiences and agentic workflows in the North platform.
• Develop evaluation, observability, and feedback systems to ensure AI reliability and effectiveness in enterprise environments.
• Collaborate with cross-functional teams to integrate LLMs into production systems.

Skills

LLM Production

AI Agents

Software Engineering

Prompt Engineering

Backend Systems

Evaluation Frameworks

Observability

Product Design

Context Construction

Tool-use Strategies

Human-AI Collaboration

Workflow Automation

Data Analysis

System Design

Regression Testing

API Integration

Job description

Cohere is building AI-powered product experiences and agentic workflows in the North platform. You will ship LLM-based features, improve observability, and implement evaluation feedback loops to ensure reliability in enterprise contexts.

We seek a strong software engineer with a proven track record of production-grade AI systems, capable of debugging complex AI failures and delivering high-quality product design insights.