ABOUT THE ROLE
Technosylva builds software that supports high-stakes, time-sensitive decisions for wildfire and natural-hazard management, and AI is a core part of how we build it. As a Senior AI Platform Engineer, you'll build and run the core services of our AI platform: gateway integrations, the skills/plugins review pipeline, the curated MCP registry, and the cost and observability tooling that shows how AI is used across the company. You'll write code, run production services and take part in on-call.
RESPONSABILITIES
- Gateway operations & integration. Configure, extend and run our AI gateway: routing, authentication, rate limits, quotas, metadata tagging, and onboarding new teams and models (cloud, third-party and on-prem).
- Skills & plugins pipeline. Build and run the review pipeline for our skills/plugins repository: automated validation, review gates, versioning and release workflows. Write and review skills, agents and plugins yourself.
- Curated MCP registry. Run the MCP server intake process, including security reviews of third-party servers, tool scoping, and allowlisting, within a published approval SLA. Build internal MCP servers when there's a gap.
- FinOps tagging & reporting. Implement cost tagging and attribution in the gateway and tools so token and compute spend can be traced to teams, products and use cases. Build the dashboards and alerts on top.
- Observability & evaluation. Instrument AI services and agents with tracing, metrics and evals, and build dashboards and alerts for latency, errors, quality and cost per request.
- Agent identity & secrets. Set up scoped, non-shared identities and secrets for agents and automations, following the platform's standards.
- Security collaboration. Work with the Security teams on MCP server and plugin reviews, incident response for AI services, and implementing controls such as access scoping, audit logging and secrets rotation.
- Model routing operations. Configure and maintain routing rules, fallbacks and load balancing across model providers, and monitor how routing affects cost, latency and output quality.
- Self-service & enablement. Build golden-path templates, CLIs and documentation so engineers can adopt AI without constant support. Help run office hours and workshops for engineers across the company.
- Operations. Join the on-call rotation, handle incidents for production AI services, and turn what you learn from incidents into fixes and runbooks.
EXPERIENCIA/HABILIDADES REQUERIDAS
- 5+ years in software, platform, DevOps or SRE engineering, building and running production services.
- Hands-on experience with LLM APIs: tool use, structured outputs, streaming, prompt caching, and the practical differences between providers (e.g. Anthropic Messages vs. OpenAI-compatible APIs).
- Experience integrating or configuring an API or LLM gateway (e.g. Azure API Management / AI Gateway, LiteLLM, Portkey, OpenRouter, Kong): routing, auth, rate limiting, tagging.
- Practical experience building with AI coding agents and their extension models (skills, plugins, MCP servers, hooks), and a clear sense of what makes them safe and maintainable.
- Strong coding skills.
- Experience with Docker, Kubernetes and infrastructure as code (Terraform or similar) on a major cloud, ideally Azure.
- CI/CD experience (GitLab CI or similar), including building automated validation and review pipelines.
- Experience collaborating with Security teams to implement security controls, remediate findings and support security reviews.
- Experience with observability tooling (OpenTelemetry, Prometheus, Grafana) and with being on call for production systems.
NICE TO HAVE
- Experience implementing MCP servers or reviewing them for security risks (prompt injection, over-scoped tools, data exfiltration).
- Experience with AI evaluation and tracing tools (Langfuse, Arize Phoenix, Braintrust, Helicone, Grafana AI Observability).
- Hands-on experience with model routing or LLM proxy tools (e.g. LiteLLM, OpenRouter, Portkey, Azure AI Foundry model router), including configuring routing rules, fallbacks and rate limits.
- Experience with cost tagging, showback/chargeback or FinOps tooling.
- Experience with agent sandboxing.
- Experience building developer tooling, CLIs, internal developer portals (e.g. Backstage) or golden-path templates.
- Awareness of AI governance and compliance requirements (EU AI Act, data classification).
BENEFITS
- Competitive annual salary.
- Private health insurance and a flexible benefits plan, allowing you to tailor part of your compensation package to your personal needs.
- Annual bonus based on individual performance and company results.
- Flexible working hours.
- Remote work options.
At Technosylva, we value diverse experiences and skills, and we understand that every career path is unique. We encourage anyone who believes they meet most of the requirements and is interested in growing and contributing in this role to apply.
DISCLAIMER
Final salary and benefits will depend on a variety of factors, including location, experience, training, qualifications, and market conditions.
EQUAL OPPORTUNITY STATEMENT
Technosylva is an Equal Opportunity Employer. We are committed to fostering an inclusive environment where diverse perspectives lead to better solutions.
