24 hours ago
Remote, MexicoSenior
Responsibilities
- Own the engineering and production reliability of Python services, APIs, automation, and integrations for AI platform administration, governance, security, privacy, and compliance.
- Design scalable AI-enabled applications and agentic workflows using enterprise model APIs and SDKs, structured outputs, tool calling, MCP, RAG, evaluations, guardrails, and human approval patterns.
- Build AI governance tooling for application inventory, onboarding, risk classification, access reviews, policy compliance, control testing, exceptions, approvals, and audit evidence.
- Establish reusable patterns for versioning, regression testing, fallback behavior, rate limiting, timeout handling, observability, and cost controls.
- Lead reliability for enterprise AI tools through SLOs, monitoring, alerting, incident response, runbooks, and post-incident improvements.
- Plan platform upgrades, configuration changes, model and vendor API migrations, and production releases with testing, rollout, rollback, and communication strategies.
- Instrument AI applications and platforms to measure latency, errors, token consumption, output quality, adoption, license utilization, security events, policy exceptions, and cost.
- Design and automate enterprise identity and access controls using SSO, SAML, OIDC, SCIM, RBAC, least privilege, and audit logging.
- Implement safeguards against prompt injection, sensitive-data disclosure, secrets leakage, insecure outputs, excessive agency, unsafe tool execution, and supply-chain risks.
- Translate SOC 2, ISO 27001, and ISO/IEC 42001 requirements into technical controls and measurable evidence across cross-functional teams.
- Evaluate AI platforms, MCP integrations, connectors, plugins, gateways, and emerging capabilities for architecture and investment decisions.
- Develop self-service provisioning, internal APIs, SDKs, infrastructure as code, and workflow integrations for scalable AI operations.
- Resolve Tier 2 and Tier 3 platform issues and maintain architecture documentation, technical runbooks, and operational playbooks.
- Partner with enablement teams and senior stakeholders to improve safe and effective AI adoption through guidance, training, and platform improvements.
Requirements
- At least 5 years of experience in platform engineering, IT operations, DevOps, or a related engineering discipline, including at least 2 years supporting SaaS or AI tooling at enterprise scale.
- Advanced Python proficiency for production services and automation, including REST services and clients, asynchronous programming, package management, type checking, automated testing, structured logging, exception handling, and secure secrets management.
- Experience designing, building, and operating REST APIs, webhooks, and event-driven workflows using OAuth 2.0 or OIDC, authorization controls, rate-limit handling, retries, idempotency, schema validation, and API version management.
- Hands-on experience delivering production AI applications or agentic workflows with enterprise model APIs or SDKs such as Anthropic, OpenAI, Amazon Bedrock, or Azure OpenAI.
- Strong enterprise identity and access management experience with SSO, SAML, OIDC, SCIM, role-based access control, least privilege, and audit logging using platforms such as Okta or Microsoft Entra ID.
- Experience with cloud infrastructure, preferably AWS, containers, and infrastructure as code using Terraform, CloudFormation, or equivalent technologies.
- Proficiency in SQL and experience designing data models, pipelines, queries, and dashboards for operational, security, compliance, cost, or usage reporting.
- Experience owning production reliability through SLOs, monitoring, alerting, on-call participation, incident management, and post-incident reviews using tools such as Datadog, CloudWatch, Splunk, Grafana, PagerDuty, or OpenTelemetry.
- Strong software engineering practices with Git, pull requests, code review, automated testing, CI/CD pipelines, and secure development practices.
- Clear written and verbal communication skills, including the ability to produce technical design documents, architecture documentation, runbooks, and stakeholder updates.
- Preferred qualifications include experience with enterprise AI identity integrations, AI platform concepts, MCP servers, AI gateways, LLM proxies, agent frameworks, vector databases, knowledge bases, embedding pipelines, RAG evaluation, enterprise architecture, systems integration, and relevant AWS, Okta, or CCSP certifications.
Benefits
- Flexible-first working culture in a global team; the role is based in Mexico.
- Mentorship, learning programs, leadership development, and education support.
- Paid volunteer time, August Free Fridays, well-being resources, and regionally tailored programs for employees and families.
- Genesys is Great Place to Work certified in 17 countries.
About Genesys
Genesys builds cloud contact center and customer experience software used by enterprises to manage voice and digital interactions, self-service, and workforce engagement. Its Genesys Cloud platform and related tools are sold as subscription services (CCaaS) with AI for routing, automation, and analytics. The company serves more than 8,000 organizations worldwide and is headquartered in Menlo Park, California.