Software Engineer, GTM AI - Python ; Brazil; Canada

About the Team

The Rev Ops team owns the systems layer, operations & automation that supports Telnyx's growth engine. Historically, that meant administering GTM tools used by humans:
Salesforce, marketing automation, enrichment vendors, routing, campaign workflows, reporting, and vendor integrations.

That operating model is changing. Telnyx is increasingly building AI agents and automation that interact directly with the GTM stack. The systems team now needs to support both human-facing workflows and bot-facing infrastructure: clean data, reliable integrations, durable automations, documented process, and scalable operating patterns.

We're looking for a Software Engineer who builds and operates the AI-native backend systems powering our go-to-market motion. You'll design multi-agent architectures, build reliable integrations across complex business systems, and own services end-to-end from prototype through production.

The systems you build orchestrate LLM-powered agents that handle real business workflows — qualifying leads, generating emails, routing meetings, enriching contacts, and managing outbound campaigns. These 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 partner with Engineering Leads and Technical Product Managers to understand the problem space, then translate those problems into well-architected, observable, and maintainable software. This isn’t prompt engineering and it isn’t gluing together SaaS tools - it’s systems engineering with AI as a core primitive.

This is a hands‑on builder role with high ownership. You’ll make architectural decisions, ship iteratively, debug production issues, and care deeply about what happens after code merges.

• Design and build multi‑agent AI systems in Python that handle complex, multi‑step business workflows – qualification, email generation, routing, enrichment, and outbound orchestration
• Architect model‑agnostic abstraction layers that decouple business logic from LLM providers, enabling flexibility across Claude, GPT, and open‑source models
• Build and operate backend services (FastAPI/Flask) deployed on Kubernetes with CI/CD, managing the full lifecycle from deployment configuration to production reliability
• Design tool‑use patterns for AI agents – structured function calling, multi‑step reasoning, state management across conversation turns, and graceful handling of model failures
• Build integrations across external systems (CRM, enrichment APIs, outreach platforms, Slack) with proper error handling, retries, rate limiting, and data contracts
• Instrument and monitor AI systems in production – build observability into agent behavior, track success rates, detect regressions, and debug non‑deterministic failures
• Design and run experiments (A/B tests, prompt variations, model comparisons) with proper evaluation infrastructure to measure what’s actually working

• 2+ years of software engineering experience building backend services in Python
• Production experience building multi‑step AI agent systems – stateful workflows where models make decisions, call tools, and operate across multiple turns, not single‑shot API wrappers
• Strong understanding of LLM internals as they affect system design: context window management, token budgets, cost/latency/capability tradeoffs across models, structured outputs, and strategies for handling hallucination and refusals
• Experience testing and evaluating non‑deterministic AI systems – you understand that assert output == expected doesn’t work and have built or used alternatives
• Solid software architecture fundamentals: API design, state management, fault tolerance, and graceful degradation when upstream services fail
• Production experience with containerized deployments (Docker, Kubernetes) and CI/CD pipelines
• Experience integrating with external APIs at scale – auth flows, rate limiting, retries, data normalization, and managing the operational complexity of multiple third‑party dependencies
• Proficiency with SQL and data…