Senior AI Engineer, Ops Labs

Félix

. Design, build, and scale autonomous AI agents for product and internal operations .

Posted 11/6/2026full-timeRemote • MexicoSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in designing and deploying production-grade AI agents, with a strong focus on LLMs and generative AI. Capable of translating operational needs into effective AI-assisted workflows while ensuring robust monitoring and stability.

Highest-signal resume keywords

Python ProgrammingLLM API ExpertiseProduction AI Agent DevelopmentCI/CD DeploymentAsynchronous Programming

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Software EngineeringAI/ML Application DevelopmentPredictive Triggers DesignDecision AutomationMonitoring and ObservabilityAutomated Evaluation PipelinesState ManagementError HandlingStructured Data ValidationMulti-Step Orchestration

Soft Skills

MentoringCollaborationProblem-Solving

Tools & Technologies

OpenAI SDKGoogle AI SDKCrewAILangChainGitGitHub

Industry Keywords

AI AgentsCX PlatformsComplianceOperational FrictionGenerative AI

Tech Stack

Tools & technologies

Python

About the role

Key responsibilities & impact

Design, build, and scale autonomous AI agents for product and internal operations
Partner with Ops leadership to transform operational friction into AI-assisted workflows
Design solutions involving predictive triggers, LLM-powered categorization, decision automation, and alert systems
Architect, ship, and maintain stateful production AI agents that call tools, move cases between queues, and maintain state across case lifecycles
Establish monitoring, tracing, and observability for agentic workflows
Integrate AI agents into CX platforms, compliance and hold queues, and transaction tooling using least-privilege access
Own containerization, CI/CD deployment, and post-launch stability
Design automated evaluation pipelines using LLM-as-a-judge, semantic similarity testing, adversarial benchmarking, and trajectory evaluations
Optimize RAG pipelines and agent loops through caching, prompt compression, and model routing
Mentor junior engineers and drive practices for asynchronous programming, error handling, and structured data validation
Define autonomy boundaries, confidence thresholds, escalation paths, approval gates, and audit trails
Partner with AI leads, engineering teams, and product managers to translate AI strategy into a roadmap

Requirements

What you’ll need

5+ years of hands-on experience in software engineering, with at least 2 years dedicated to building and deploying production-grade AI/ML applications focused on LLMs or generative AI
Mandatory expertise in Python
Deep familiarity with at least one core LLM API or framework, such as OpenAI SDK, Google AI SDK, CrewAI, or LangChain
Proven experience shipping production AI agents that take actions, including tool calling, multi-step orchestration, state management, human-in-the-loop escalation, guardrails, and failure handling
Strong understanding of software development best practices, Git/GitHub, and CI/CD pipelines
Ability to translate ambiguous operational briefs into testable hypotheses and validate assumptions through experiments
Ability to translate high-level business needs into concrete, maintainable, and well-tested code
Experience building AI for CX, support, compliance, or other operations teams
Equivalent competencies in the listed areas will also be considered

Benefits

Comp & perks

Competitive salary
Initial stock options grant
Annual performance bonus
Unlimited PTO
Paid parental leave
Work model: currently fully remote, with a future transition to a hybrid setup
Health, dental, and vision plans
Continuous learning opportunities
Empowering opportunities for growth in a dynamic entrepreneurial environment