Senior AI Platform Engineer
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Senior AI platform engineer operating gateways, MCP services and observability for Technosylva’s wildfire-management software. Building secure, cost-aware production AI infrastructure.
Responsibilities:
- Build and run core AI platform services, including gateway integrations, skills/plugins review pipelines, a curated MCP registry, and cost and observability tooling
- Configure, extend and operate the AI gateway for routing, authentication, rate limits, quotas, metadata tagging, and onboarding teams and models
- Build and operate automated validation, review gates, versioning and release workflows for skills and plugins
- Write and review skills, agents and plugins
- Run MCP server intake, security reviews, tool scoping and allowlisting; build internal MCP servers when needed
- Implement cost tagging and attribution for token and compute spend, and build dashboards and alerts
- Instrument AI services and agents with tracing, metrics and evaluations; monitor latency, errors, quality and cost per request
- Set up scoped identities and secrets for agents and automations
- Collaborate with Security teams on reviews, incident response, access scoping, audit logging and secrets rotation
- Configure model routing rules, fallbacks and load balancing across model providers
- Build golden-path templates, CLIs and documentation; support office hours and engineering workshops
- Participate in the on-call rotation, handle production incidents and create fixes and runbooks
Requirements:
- 5+ years in software, platform, DevOps or SRE engineering, building and running production services
- Hands-on experience with LLM APIs, including tool use, structured outputs, streaming and prompt caching
- Practical understanding of differences between LLM providers, including Anthropic Messages and OpenAI-compatible APIs
- Experience integrating or configuring an API or LLM gateway, including routing, authentication, rate limiting and tagging
- Practical experience building with AI coding agents and extension models, including skills, plugins, MCP servers and hooks
- Strong coding skills
- Experience with Docker, Kubernetes and infrastructure as code such as Terraform on a major cloud, ideally Azure
- CI/CD experience such as GitLab CI, including automated validation and review pipelines
- Experience collaborating with Security teams to implement controls, remediate findings and support security reviews
- Experience with observability tooling such as OpenTelemetry, Prometheus and Grafana
- Experience being on call for production systems
Benefits:
- Competitive annual salary
- Private health insurance
- Flexible benefits plan allowing part of the compensation package to be tailored to personal needs
- Annual bonus based on individual performance and company results
- Flexible working hours
- Remote work options
Similar Jobs
Staff AI Platform Engineer
Staff AI Platform Engineer owning gateways, agent orchestration, governance, and observability. Building AI infrastructure for Technosylva’s wildfire and natural-hazard management software.
Platform Engineer – III
Platform Engineer III projetando infraestrutura cloud, Kubernetes e observabilidade para o ecossistema de beleza do Grupo Boticário. Automatizando plataformas escaláveis com Terraform, GitOps e AWS.
Platform Engineer
Platform Engineer operating PH360, a public health technology platform for government agencies. Managing AWS, Salesforce, CI/CD, observability, and compliance infrastructure.
Lead Software Engineer, Platform Engineering
Lead full-stack platform engineer building internal platforms, CI/CD automation, and developer tools. Supporting ITHAKA’s JSTOR, Portico, and Ithaka S+R education-access mission.
Staff Frontend Engineer – Platform
Staff Frontend Engineer building Grafana Cloud usage, billing, and account platforms. Developing TypeScript/React interfaces, backend services, and integrations for SaaS operations.
Staff Frontend Engineer – Platform
Staff Frontend Engineer building Grafana Cloud customer portals, usage metering, and billing integrations. Leading reliable full-stack systems across Grafana, NetSuite, Salesforce, and cloud marketplaces.
Senior Director – Applied AI Architecture, Platform Infrastructure
Senior AI architecture leader building GuideWell’s enterprise healthcare AI platforms and applied research capability. Establishing secure, scalable AI infrastructure and standards for regulated healthcare.
Senior Corporate Enterprise Platform Engineer, Windows
Senior Windows endpoint engineer owning endpoint reliability, Intune, patching, and automation. Improving platform operations for Dropbox’s cloud file collaboration service.
Senior Corporate Enterprise Platform Engineer, Windows
Senior Windows endpoint engineer improving Dropbox’s corporate device platform. Automating Intune-based provisioning, patching, fleet health, and code-managed endpoint operations.
Senior Staff Platform Engineer – Core
Senior Staff Platform Engineer leading AWS, Kubernetes, CI/CD, and observability initiatives. Building platform infrastructure for Fanatics’ global commerce, collectibles, and betting sports platform.
Platform Engineer
Platform Engineer building AWS cloud-native APIs, SDKs, CLIs, and services for DTN’s operational decisioning platform. Developing distributed systems and AI-augmented capabilities used by engineers and enterprise customers.
Senior Platform Engineer, MarTech
Senior Platform Engineer operating Braze, Hightouch, and customer-data integrations. Supporting Twin Health’s AI-powered metabolic healthcare platform and member engagement.
Platform Engineer
Platform Engineer building scalable Kubernetes and cloud infrastructure for Avaya’s enterprise communications software. Automating deployments, reliability, security, and platform operations through DevOps practices.
Senior Platform Engineer, AI Applications
Senior Platform Engineer building production AI services, APIs, cloud infrastructure, and enterprise integrations. Supporting Improvix Technologies’ secure federal technology programs.
Platform Engineer
Platform Engineer building scalable AWS infrastructure, automation, and observability for Resend’s modern email platform. Improving reliability and developer tooling for teams worldwide.
Platform Engineer
Platform Engineer building reliable, secure AWS infrastructure for Resend’s developer email platform. Improving observability, automation, and self-service tooling for engineering teams.
Director of Platform Engineering
Director of Platform Engineering leading GCP infrastructure, DevOps, security, and AI automation. Scaling Author Health’s patient care platform and managing a high-performing engineering team.
Senior AI Platform Engineer
AI Platform Engineer construyendo plataformas Kubernetes, GPU y MLOps para evoila, líder europeo en cloud e infraestructura. Diseñando soluciones de IA escalables para clientes de múltiples sectores.
BI Platform Developer
BI Platform Developer building Power BI dashboards, semantic models, and cloud analytics platforms for Keypath Education’s online university programs. Improving BI governance, deployment, and data-driven education access.
Senior Software Engineer – Platform
Senior Platform Engineer building reliable cloud infrastructure for Astronomer’s Apache Airflow DataOps platform. Owning scalable testing, deployment, observability and reliability practices.