About Metacto
At Metacto, we partner with companies across industries to transform how work gets done. We build AI agents and agentic workflows across customer operations, finance, revenue, support, and beyond.
Working at Metacto means tackling a constantly changing mix of ambitious, real-world problems. You might redesign a critical business workflow, connect fragmented systems and data, or build an agent that becomes part of a client’s daily operations. You’ll contribute across the full lifecycle, from understanding the business problem to designing, shipping, evaluating, and continuously improving the solution in production.
We move quickly, give people meaningful ownership, and measure our success by the business outcomes we create. If you want to work at the forefront of applied AI, solve challenging problems across a diverse set of clients, and help define how agentic software is built and deployed, we’d love to hear from you.
Job Overview
We’re looking for a Jr AI Engineer to build production agent systems alongside the engineers leading our operational AI engagements.
You are early in your career and you want to learn what production AI actually takes. You will work inside real client systems in your first month, against patterns set by engineers who have shipped this before, on a team small enough that your work reaches production instead of sitting in a branch.
Key Responsibilities
- Build Applied AI Features: Implement well-specified services, workflows, and reusable components for LLM-powered automation, retrieval, tool use, summarization, classification, and knowledge workflows.
- Collaborate with Senior Engineers: Work alongside the senior engineers leading an engagement, implement against the architecture and reusable patterns they set, take direction through code review and pairing, and grow toward owning an agent end to end.
- Integrations and Data Plumbing: Connect agents to the systems clients actually run, including CRMs, ticketing, data warehouses, and internal APIs, with attention to authentication, pagination, rate limits, retries, error handling, and inconsistent source data.
- Evaluation and Regression Testing: Write eval cases, test rows, and regression checks against the thresholds in an agent’s charter, and investigate the failure modes that only appear against real client data.
- Observability and Incident Response: Read traces, dashboards, and logs to understand how an agent behaved in production, and raise incidents the moment behavior drifts from what the evals said it would do.
- Secure Handling of Client Data and Access: Work within the client’s access model, deploy runbooks, and data-handling rules, covering credentials, secrets, permissions, and PII boundaries across every environment you touch.
- Quality Gates and Release Readiness: Take each piece of work through the production agent checklist, covering tools, skills, positive and negative evals, and human review steps, before release.
- Documentation and Knowledge Sharing: Maintain runbooks, integration notes, and eval documentation, participate in design reviews and retrospectives, and sit in on client working sessions to see how technical decisions get made.
Requirements
- 1+ years building software, or a portfolio of real projects that stand on their own without explanation.
- Fluency in one language, ideally Python or TypeScript, and comfort reading code you did not write.
- Hands-on experience with LLM APIs, prompting, and at least one retrieval or agent framework outside a tutorial.
- Something you shipped that real people used, however small, with every decision in it still explainable.
- Comfort working under code review and technical direction from senior engineers.
- Daily proficiency with AI development tools. We weigh the quality of your direction, not whether you typed every line.
Preferred Qualifications
- Exposure to evals, tracing, or observability tooling in a real project.
- Any production experience: on call, a deploy you owned, an incident you sat through.
- A public repo you would be happy to walk us through end to end.
Position Details
- Type: Full-Time
- Location: Remote (US) or nearshore
- Base Salary Range (US): $90,000 - $115,000
- Nearshore: $3,000 - $4,500 USD / month
- Reports to the Head of Engineering
- Not client-facing; you work behind an engagement, not in front of one
Benefits
At Metacto, we believe that great work starts with a great workplace. We offer a competitive total rewards package that supports your well-being, growth, and financial security.
Our benefits include:
- 100% remote work with flexibility to manage your schedule
- Unlimited paid vacation to recharge and maintain work-life balance
- 401(k) plan with a 400% company match on the first 6% deferred
- Comprehensive medical, dental, and vision insurance
- Health Savings Account (HSA) and Flexible Spending Account (FSA) options
- Group term life insurance, plus additional coverage options
How We Hire
- A 30-minute intro with our Head of Engineering
- A look at one of your public repos, discussed with you
- A working session on a real engagement problem, sanitized
- A values conversation with our CEO
No take-home that eats your weekend. If the working session runs long at the senior level, we pay for it.
Not sure which level you are? Apply to the one closest and tell us what you have shipped. We level in the process.