S
Agent Engineer (Remote — Worldwide)
FeaturedPythonTypeScriptLLMs (GPT-4, Claude)RAGPrompt EngineeringAPI IntegrationLangChain / LlamaIndexDistributed SystemsVector DatabasesModel Evaluation
About the role
Sierra is seeking an Agent Engineer to build the next generation of conversational AI agents that power mission-critical customer experiences for the world's leading brands. You will be responsible for architecting sophisticated agentic workflows that handle high-stakes reasoning, complex tool usage, and seamless integration with enterprise systems. This role is pivotal in ensuring our agents are not only conversational but also reliable, safe, and deeply integrated into the operational fabric of our partners.
Responsibilities
- Design and implement multi-step agentic workflows that leverage LLMs to perform complex reasoning and task execution.
- Build robust integrations between Sierra’s agent platform and various enterprise backends, including CRM and ERP systems.
- Optimize agent performance for low latency and high reliability while navigating the nuances of different model providers.
- Develop and refine evaluation suites to ensure agent responses are accurate, brand-compliant, and secure.
- Collaborate with Product and Design teams to translate customer business logic into executable AI behaviors.
- Contribute to the core Sierra platform by building reusable components and patterns for agent development.
- Participate in an on-call rotation to ensure the stability of production agents for global enterprise clients.
Requirements
- 4+ years of experience in software engineering, with a strong focus on Python or TypeScript.
- Hands-on experience building production-grade applications using Large Language Models (LLMs) and orchestration frameworks.
- Deep understanding of prompt engineering, RAG (Retrieval-Augmented Generation), and agentic reasoning patterns.
- Strong background in building and consuming complex APIs and managing distributed system architecture.
- Experience with evaluation frameworks and techniques to measure LLM performance and reliability in production.
- Demonstrated ability to work autonomously in a fully remote, fast-paced startup environment.
- Professional fluency in English with exceptional technical communication skills across time zones.
Benefits
Equity, healthcare, learning budget.
Disclaimer: MMagic.ai connects talented people with AI companies around the world. While we work hard to feature quality opportunities, we don't independently verify employers, candidates, salaries, or hiring outcomes. We encourage you to research each opportunity and company before applying or making an offer.