About this role.
This AI Agent Engineer role builds, operates, evaluates, and retires autonomous AI agents that improve internal performance and customer outcomes. The engineer will partner with department leaders to identify high-value use cases, integrate agents with internal and third-party tools, and measure business results. Core technical expectations include experience with autonomous agents, frontier and open-source models, Go, TypeScript, GraphQL, Postgres, and GCP. The position requires strong written English and the ability to translate AI capabilities into practical solutions for non-specialist stakeholders. It is a fully remote, full-time engineering role with significant ownership over experimentation and production adoption.
Role DNA
A quick view of the complexity, pace, ownership and collaboration implied by the job description.
Job Complexity
5/5Pace & Pressure
5/5Autonomy Level
5/5Communication Load
4/5Salary analysis
Estimated compensation compared with the broader US market for similar roles.
Core skills
Skills and capabilities most closely associated with this opportunity.
Sample interview questions
I would explain the business problem, the agent's permitted actions, tools and data sources, orchestration logic, guardrails, and escalation path. I would also quantify outcomes such as time saved, accuracy, throughput, cost, or user adoption, and describe how I monitored failures.
I would interview stakeholders and map repetitive, high-volume, measurable workflows with accessible data and a clear owner. I would prioritize use cases by expected impact, implementation effort, operational risk, and the ability to run a controlled pilot with baseline metrics.
I would define task-specific success metrics before launch, including completion quality, error rate, human-review rate, latency, cost, and business impact. I would compare results with a baseline, review failure patterns, and remove or redesign the agent if it cannot meet a justified quality and ROI threshold.
I would apply least-privilege credentials, allowlisted actions, structured tool schemas, input validation, audit logs, rate limits, approval gates for consequential actions, and robust retry and rollback behavior. I would test adversarial and malformed inputs and ensure sensitive data is minimized and protected.
I would benchmark candidate models on representative tasks using quality, reliability, latency, cost, context requirements, tool-use behavior, privacy constraints, and operational support. I would select the model that best meets the agent's measurable requirements and maintain an evaluation suite to reassess choices as models change.
Sticker Mule is building the most lucrative commerce platform on the Internet by combining software, manufacturing, and AI in one stack.
We’re hiring an engineer to build, run and manage a team of AI agents to help us innovate faster, improve performance, and better serve customers.
Work performed
Identify where agents can help and build them accordingly.
Work with department leads to assess AI needs.
Help connect agents to appropriate third-party and internal tools.
Measure results and remove agents that don’t deliver.
Test new tools and models as they ship and adopt what works.
Advise others on AI capabilities to help them perform.
Requirements
Experience building agents that run on their own and do meaningful work
Strong with Grok, Claude, OpenAI, and open source
Comfortable in Go, TypeScript, GraphQL, Postgres, GCP
Writes clearly in English
Compensation
Salary: $150,000–$250,000 USD
$20,000 signing bonus
4 weeks vacation + country-specific holidays
Fully remote
Upload your resume now
- To unlock remote work opportunities and be discovered by global employers.
This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content.
