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 Staff AI Platform Engineer, you'll own the architecture and technical direction of our AI platform: the AI gateway, MCP registry, skills and plugins, evaluation and observability, security and governance. This is a hands-on role: you'll design systems, write code, run production services and take part in on-call.
RESPONSABILITIES
- Own the AI Platform architecture. Set the technical vision and standards that engineers, product, and other practitioners build against, and keep the architecture documented.
- Gateway & model routing. Lead the evolution of our AI gateway and the build-vs-buy decisions around it: provider routing, hybrid and on-prem model routing policy, failover, caching, rate limits, and multi-provider compatibility (Anthropic Messages vs. OpenAI-compatible APIs).
- Agent orchestration & runtime. Decide the orchestration stack (native agent harnesses vs. provider-agnostic runtimes) upon collaboration with pro users, design sandboxing and lifecycle management for agents that run code or touch internal systems, and set the multi-agent and human-in-the-loop patterns.
- Identity, access & governance. Design identity and access control for both people and non-human agent identities: scoped credentials, least privilege, audit trails and kill-switches. Lead approved model/tool/MCP allowlists and access tiers, and work with Legal and Security on EU AI Act and data-classification requirements.
- Skills, plugins & MCP ecosystem. Shape how our skills/plugins repository evolves (review gates, version pinning, namespacing, support for more agents) and define the security model for the curated MCP registry.
- Evaluation & observability. Choose and standardize the tooling for tracing agent decisions, running evals and detecting drift and quality regressions across AI applications, so failures are caught early and can be supported properly on call.
- FinOps for usage-based AI. Design the cost attribution and allocation framework for token and compute spend (per team, product and use case), with a measurable baseline and a named business owner for each use case so its value can be measured.
- Escalation point for embedded delivery. Be the technical escalation point when working alongside engineering and other business units on AI use cases. Unblock, review designs, and turn what you learn into golden paths.
- Security partnership. Work closely with the Security teams to threat-model AI systems and agents, define controls for prompt injection, data exfiltration and over-privileged tools, and align AI platform standards with company security policies.
- Raise the bar. Mentor engineers on the platform and across the company's AI community, run design reviews and RFCs, and represent AI Platform in engineering-wide technical decisions.
- Take part in the on-call rotation and incident response for production AI services.
REQUIREMENTS
- 8+ years in software, platform, infrastructure or SRE engineering, including time in a Staff/Principal-level or tech-lead role where you owned architecture across teams.
- Strong understanding of LLM and API fundamentals: context windows, tool use, structured outputs, streaming, prompt caching, and the differences between providers' APIs.
- Hands-on experience designing or running an LLM gateway or similar layer (e.g. Azure API Management / AI Gateway, LiteLLM, Portkey, OpenRouter, Bifrost, TrueFoundry), including making build-vs-buy decisions.
- Experience with agent orchestration patterns: multi-agent workflows, delegation, human-in-the-loop approval gates, memory and context management, token optimization.
- Experience working with Security teams on threat modelling, security reviews and risk acceptance for production systems, ideally including AI or agent-based workloads.
- Working knowledge of the Model Context Protocol (MCP): implementing servers, scoping tools, and reviewing third-party servers for security.
- Production experience with containers and isolation (Docker, Kubernetes).
- Infrastructure as code (Terraform or similar) on at least one major cloud, ideally Azure.
- A solid grasp of observability (OpenTelemetry, Prometheus, Grafana) and reliability engineering, and of how they apply to non-deterministic AI systems.
- Strong coding skills.
- A record of influencing without authority: writing clear RFCs and architecture decision records, getting teams to agree, and explaining technical trade-offs to non-technical stakeholders.
NICE TO HAVE
- Experience with AI evaluation and observability tools (Langfuse, Arize Phoenix, Braintrust, Helicone, Grafana AI Observability).
- FinOps experience with usage-based cost models: tagging, chargeback/showback, budgets and anomaly detection.
- Familiarity with AI governance frameworks (EU AI Act, NIST AI RMF, ISO/IEC 42001) and experience partnering with Legal or Compliance.
- Experience with AI coding agents and their extension models (e.g. Claude Code skills, plugins, hooks, subagents).
- Hands-on experience designing or evaluating model routing solutions (e.g. LiteLLM, OpenRouter, Portkey, Azure AI Foundry model router, RouteLLM, Not Diamond), including fallback, load balancing and cost- or quality-based routing.
- Experience serving self-hosted or on-prem models (vLLM, Triton, KServe or similar).
- Experience building developer platforms, golden paths or internal developer portals (e.g. Backstage).
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.
