Full-Stack Engineer, AI Agents

ABOUT THE ROLE Join a small, early-stage team building production AI systems for freight and logistics workflows. You will own work end to end, from understanding customer needs through implementation, deployment, and production monitoring, with a focus on voice and email agents. WHAT YOU'LL DO - Scope customer problems, build features across the stack, deploy them, and monitor production behavior. - Develop voice and email agents, including speech pipelines, LLM orchestration, and deterministic safeguards for prices, terms, and actions. - Create evaluation systems using golden datasets, offline and online checks, regression and hallucination testing, and tool-call correctness checks. - Build embedding-based retrieval and matching with reranking, balancing quality, latency, and cost. - Instrument production systems and use observability and rollout strategies to improve reliability. WHAT WE'RE LOOKING FOR - At least 5 years of professional software engineering experience shipping production software with end-to-end, full-stack ownership. - Hands-on experience taking LLM features to production, including architecture, tool-calling, retrieval, and robust evaluation. - Production experience with React, Next.js, Supabase, and Python. - Experience with agent or voice tooling such as Pipecat, LangChain, LiveKit, or equivalent technologies. - Strong system design fundamentals, including streaming, concurrency, SQL, and reasoning about scale and cost. - Experience with production observability and deployment rollouts, and daily use of generative AI coding tools with careful verification. - Voice or real-time systems experience, early-stage engineering experience, or experience building complex tool-use systems is valuable. COMPENSATION & BENEFITS Compensation is $5,000 to $9,000 USD monthly. Visa sponsorship is not available. LOCATION Fully remote, based in Latin America.