SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Telnyx is building the next generation of global connectivity infrastructure and is now expanding into AI-native go-to-market systems. The RevOps team is evolving from managing traditional GTM tools (Salesforce, marketing automation, enrichment vendors) to operating AI agents and automation that directly interact with the GTM stack.
You'll join as a Software Engineer focused on building and operating the backend systems powering AI-driven go-to-market workflows. This role sits at the intersection of systems engineering and AI—you'll design multi-agent architectures that handle real business processes: lead qualification, email generation, meeting routing, contact enrichment, and outbound campaign orchestration.
The systems you build are stateful, multi-step agent systems running on Kubernetes that make decisions, call tools, and interact with external APIs under real constraints: rate limits, token budgets, cost targets, and data quality issues. You'll architect model-agnostic abstraction layers that decouple business logic from LLM providers (Claude, GPT, open-source models), enabling flexibility and portability.
Key responsibilities include designing and building multi-agent AI systems in Python; architecting backend services (FastAPI/Flask) deployed on Kubernetes with full CI/CD ownership; designing tool-use patterns for agents including structured function calling, multi-step reasoning, and state management; building integrations across external systems (CRM, enrichment APIs, outreach platforms, Slack) with proper error handling and retries; instrumenting and monitoring AI systems in production to track success rates and detect regressions; and designing and running experiments to measure what's actually working.
This is a hands-on builder role with high ownership. You'll make architectural decisions, ship iteratively, debug production issues, and care deeply about reliability and observability. You're not doing prompt engineering or gluing together SaaS tools—you're doing systems engineering with AI as a core primitive.
