Solutions Architect - AI Model Specialist

About the job

FriendliAI is seeking a Solution Architect specializing in open-source AI models, AI inference API integration, and agentic systems. You will work closely with our customers to integrate FriendliAI's inference and agent frameworks into real-world products, enabling them to build and scale AI applications effectively.

You will work directly on our customers' projects, collaborating with their engineering teams to solve challenges in integrating tools, environments, and models with AI agents. This is a hands-on, customer-embedded role.

Key Responsibilities

Design and implement AI-powered products using FriendliAI's APIs

Guide customers on selecting, evaluating, and operating AI models across different domains

Integrate and extend open-source frameworks for FriendliAI integration

Build and deploy custom inference endpoints, chat flows, and multi-agent orchestration pipelines

Develop SDKs, example applications, and reference APIs for agentic and generative AI use cases

Provide deep technical guidance on prompt engineering, API composition, and workflow orchestration

Debug and optimize context and memory across long-running agent sessions

Gather customer feedback and translate it into product-level improvements

Lead technical demos, developer workshops, or webinars

Qualifications

3+ years of software engineering experience, ideally in backend or API development

Proficient in Python and modern web frameworks (FastAPI, Flask, or similar)

Strong experience deploying LLMs and integrating into generative AI APIs

Familiarity with agentic AI frameworks (LangChain, CrewAI, AutoGen, etc.)

Strong experience in integrating open-source generative AI models into applications

Excellent communication skills and a passion for improving developer experience

Excellent problem-solving and debugging skills in real-world environments

Preferred Experience

Contributions to open-source AI libraries or projects

Familiarity with multi-agent orchestration, memory systems, RAG, and workflow DAGs

Experience with serverless backends or API gateways

Benefits

A front-row seat to the generative AI infrastructure revolution

Competitive compensation and benefits package

Daily lunch and dinner provided; unlimited snacks and beverages

Health check-up and top-tier hardware support

Flexible working hours and a highly collaborative environment

About us

FriendliAI is building the next-generation AI inference platform that accelerates the deployment of large language and multimodal models with unmatched performance and efficiency. Our infrastructure powers high-throughput, low-latency workloads for global organizations and integrates directly with Hugging Face, providing instant access to over 500,000 open-source models. We are on a mission to deliver the world's best platform for AI inference.