5 hours ago
Milan, ItalyMid Level
Responsibilities
- Embed with enterprise customers to understand communications workflows, AI use cases, and integration challenges.
- Design architectures and build, deploy, and operate custom implementations involving AI voice assistants, Telnyx APIs, WebRTC, and LLM systems.
- Deploy and manage LiteLLM gateways, model routing, fallbacks, usage governance, observability, guardrails, and customer-hosted model stacks.
- Build production observability with metrics, logs, traces, dashboards, alerting, and operational runbooks.
- Lead technical discovery, POCs, pilots, production launches, and customer outcomes through stable go-live.
- Design model routing and prompt/RAG pipelines, evaluation harnesses, and portable application architectures for multilingual and EU-regulated use cases.
- Collaborate with Product and Engineering based on field insights and troubleshoot complex integrations with customer teams.
- Create clear technical documentation and maintainable solutions for handoff.
Requirements
- A CS degree or equivalent experience.
- At least 3 years of experience building and shipping production software used by real customers.
- Proficiency in Python, Node.js/TypeScript, and Go.
- Production understanding of model rate limits, quotas, timeouts, retries, streaming, token accounting, cost attribution, and concurrency failures.
- Experience deploying containerized services on Kubernetes with secrets management, configuration, and upgrades.
- Hands-on observability experience with Prometheus, Grafana, OpenTelemetry, Graylog, ELK, or equivalent tools.
- High-concurrency experience with Kafka, message queues, or event streams, including partitioning, consumer groups, backpressure, and consumer lag.
- Experience building APIs with OpenAPI, REST or GraphQL design, authentication, rate limiting, versioning, and idempotency.
- Exposure to SIP, WebRTC, or real-time voice and messaging systems.
- Customer-facing engineering experience, including technical discovery, executive presentations, whiteboarding, and live troubleshooting.
- Excellent written and verbal communication in English and Italian.
- Legally authorized to work in Italy or eligible for sponsorship.
- Preferred experience includes AI voice assistants, speech-to-text/text-to-speech, LLM evaluation, LLM gateways, open-weight models, inference serving, SQL, ETL, CI/CD automation, telecom or CPaaS, sovereign or on-premise deployments, EU regulatory frameworks, and security practices.
Benefits
- Hybrid role based in Milan, with relocation considered.
- Travel across Italy, Spain, and Greece.
- Opportunity to work directly with enterprise customers and influence Telnyx Product and Engineering roadmaps.
Tech Stack
Categories
Forward Deployed
About Telnyx
Telnyx builds a communications platform and AI infrastructure for developers and enterprises, offering SIP trunking, voice and messaging APIs, WhatsApp Business, eSIM/IoT connectivity, and low-latency inference on a private global IP network. The privately held company, founded in 2009 and headquartered in Austin, operates worldwide and holds a Saudi VVSP license with regional anchorsites for data locality. Revenue comes from usage-based APIs and enterprise connectivity services.