FriendliAI is hiring a Python Engineer to build developer tools for our users and internal engineers. The software developed by the engineer will be the primary way developers integrate with our inference and agent platform. Your work will remove friction for internal teams and external users. You’ll design ergonomic & stable APIs, reliable releases to PyPI, and drive top-tier developer experience across documentation, examples, and tooling. You’ll collaborate with frontend engineers on end-to-end workflows and partner with product & engineering teams.
Key ResponsibilitiesOwn the Python SDK lifecycle. You will design APIs and implement the client side in the SDK.
Build and maintain a cross-platform CLI with a modern interface, including helpful error messages and good UX.
Manage packaging and distribution pipelines.
Develop and maintain internal developer tools related to DevOps.
Create examples, templates, and guides that help developers effectively utilize our software bundles.
3+ years of professional Python engineering building libraries, SDKs, or developer tools used in production.
Demonstrated SDK/CLI ownership. Familiarity with API ergonomics and versioning, deprecation policies, telemetry, and debugging customer issues.
Strong Python fundamentals, including asyncio, typing, packaging, and testing.
Web API fluency in REST and gRPC.
Experience working with Python monorepos.
Clear written communication skills and capable of turning complex features into clean APIs and concise docs.
Maintainer or significant OSS contributor in Python libraries (tooling, SDK, CLI, etc.).
Experience with Python AST and Meta-programming, Packaging
Performance work (profiling, streaming, backpressure) or multi-platform build experience.
Cross‑language exposure (TypeScript/Node, Go).
Containers & local dev tooling (Docker); familiarity with Kubernetes basics.
Experience with LLM/agent SDKs or inference workflows.
Flexible working hours
Daily lunch and dinner provided; unlimited snacks and beverages
Supportive and highly collaborative work environment
Health check-up support and top-tier equipment/hardware support
A front-row seat to the generative AI infrastructure revolution
Competitive compensation, startup equity, health insurance, and other benefits.
FriendliAI 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 500,000 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.
Skills Required
- 3+ years professional Python engineering building libraries, SDKs, or developer tools used in production.
- Demonstrated SDK/CLI ownership including API ergonomics, versioning, deprecation policies, telemetry, and debugging customer issues.
- Strong Python fundamentals, including asyncio, typing, packaging, and testing.
- Web API fluency in REST and gRPC.
- Experience working with Python monorepos.
- Clear written communication skills and ability to produce concise docs, examples, and guides.
- Manage packaging and distribution pipelines (PyPI releases).
- Maintainer or significant OSS contributor in Python libraries (tooling, SDK, CLI, etc.).
- Experience with Python AST and meta-programming, packaging.
- Performance work (profiling, streaming, backpressure) or multi-platform build experience.
- Cross-language exposure (TypeScript/Node.js, Go).
- Containers & local dev tooling (Docker); familiarity with Kubernetes basics.
- Experience with LLM/agent SDKs or inference workflows and familiarity with Hugging Face integrations.
What We Do
FriendliAI is The Frontier AI Inference Cloud: an AI infrastructure platform that deploys, scales, and monitors large language and multimodal models. Its inference engine maximizes GPU utilization to deliver faster performance and steep cost savings for open-weight and custom models, while offering enterprise-grade reliability, SLAs, and compliance to help teams run generative AI and agent workloads at production scale.
