Friendliai

Software Engineer – AI Agents

San Francisco, Remote. Posted 7 months ago

The role

You will design and build agentic features including document understanding, advanced RAG, and customer support automation. You will develop the Friendli Agent API and build production-ready agent applications in Python.

What you will do

  • Design, build, and maintain agent APIs and applications
  • Evaluate and integrate open-source models
  • Develop reference agent applications to showcase workflows
  • Collaborate with backend and infrastructure teams
  • Ensure APIs are robust, developer-friendly, and enterprise-ready
  • Improve reliability, scalability, and performance of agent features

Required qualifications

  • 3+ years of experience in software engineering, preferably in backend, ML systems, or API development
  • Bachelor’s or Master's degree in Computer Science, Computer Engineering, or equivalent
  • Strong programming skills in Python
  • Experience with various Python frameworks
  • Solid understanding of LLM workflows, agent patterns, or tool invocation systems
  • Experience designing and delivering production APIs
  • Familiarity with open-source LLMs and multimodal models (HuggingFace, LangChain, LlamaIndex, etc.)
  • Strong foundations in cloud-native development

Nice to have

  • Experience with document understanding pipelines (e.g., OCR, RAG, summarization, structured extraction)
  • Familiarity with Kubernetes or container orchestration in production
  • Built or contributed to agent frameworks, SDKs, or CLIs
  • Have worked in a startup or fast-paced environments with ownership and ambiguity
  • Passion for developer experience and enabling AI adoption

Benefits

  • Flexible working hours
  • Daily lunch and dinner provided
  • unlimited snacks and beverages
  • Supportive and highly collaborative work environment
  • Health check-up support
  • top-tier equipment/hardware support
  • Competitive compensation
  • startup equity
  • health insurance

About the company

FriendliAI is building an AI inference platform that makes large language and multi-modal models fast, efficient, and deployable at scale. They power high-throughput, low-latency AI workloads for organizations worldwide.