Software Engineer

Agent EngineerWe're seeking an Agent Engineer to design and build agentic features in our platform, including document understanding, advanced RAG, and customer support automation. In this role, you will develop not only the agent components themselves, but also the Friendli Agent API, which serves as the core developer interface for building and extending agent applications. You will also build agent applications as production-ready examples of how agents can solve real-world problems.These applications will be primarily written in Python and will serve as reference implementations for our customers and community. We are looking for a hands-on engineer who is passionate about building agent systems and making AI easy for developers to adopt. The ideal candidate is comfortable creating agent applications that showcase what is possible, is curious about and experienced with open-source models, and enjoys turning them into reliable, high-impact features.Key ResponsibilitiesDesign, build, and maintain agent APIs and applications that deliver document understanding and other high-value featuresEvaluate and integrate open-source models to power production-ready agent features where possibleDevelop reference agent applications to showcase workflows and accelerate customer adoptionCollaborate with backend and infrastructure teams to integrate agents with deployment, orchestration, and monitoring systemsEnsure APIs are robust, developer-friendly, and enterprise-ready through strong design principles and documentationContinuously improve the reliability, scalability, and performance of agent features in productionQualifications3+ years of experience in software engineering, preferably in backend, ML systems, or API developmentBachelor's or Master's degree in Computer Science, Computer Engineering, or equivalentStrong programming skills in Python; experience with various Python frameworksSolid understanding of LLM workflows, agent patterns, or tool invocation systemsExperience designing and delivering production APIsFamiliarity with open-source LLMs and multimodal models (HuggingFace, LangChain, LlamaIndex, etc.)Strong foundations in cloud-native developmentPreferred ExperienceExperience with document understanding pipelines (e.g., OCR, RAG, summarization, structured extraction)Familiarity with Kubernetes or container orchestration in productionBuilt or contributed to agent frameworks, SDKs, or CLIsHave worked in a startup or fast-paced environments with ownership and ambiguityPassion for developer experience and enabling AI adoptionBenefitsFlexible working hoursDaily lunch and dinner provided; unlimited snacks and beveragesSupportive and highly collaborative work environmentHealth check-up support and top-tier equipment/hardware supportA front-row seat to the generative AI infrastructure revolutionCompetitive compensation, startup equity, health insurance, and other benefits.About FriendliAIFriendliAI is building the world's best AI inference platform that makes large language and multi-modal models fast, efficient, and deployable at scale. We power high-throughput, low-latency AI workloads for organizations worldwide and integrate directly with Hugging Face, giving developers instant access to over 600,000 open-source models.We are a small, fast-moving team doing work that matters at one of the most exciting moments in the history of technology. With our world-class inference engine, we are building a platform that the AI industry can actually rely on.