Founding Engineer

We're looking for a Founding Engineer with deep AI infrastructure experience to design, build, and scale the systems that power our products. This is a hands-on, high-ownership role: you'll own everything from model serving and inference optimization to data pipelines, evaluation frameworks, and the cloud infrastructure underneath it all.

Requirements:

• Architect and build the core AI infrastructure stack — model serving, inference pipelines, orchestration, and scaling
• Design and optimize LLM-based systems, including RAG pipelines, agentic workflows, fine-tuning infrastructure, and prompt/eval frameworks
• Build reliable, observable, cost-efficient inference systems (latency, throughput, and GPU utilization optimization)
• Stand up and own cloud infrastructure (AWS/GCP/Azure), CI/CD, containerization, and orchestration (Docker, Kubernetes)
• Build data pipelines for ingestion, processing, embedding, and retrieval at scale
• Establish engineering foundations — testing, monitoring, deployment practices, and security — that the team will build on for years
• Work directly with founders on product direction, technical strategy, and early customer deployments
• Help recruit, interview, and mentor the engineers who come after you

What we're looking for:

• 4+ years of software engineering experience, with significant time spent on ML/AI infrastructure, platform engineering, or backend systems at scale
• Hands-on experience deploying and scaling LLM applications in production (model serving frameworks such as vLLM, TGI, Triton, or managed equivalents)
• Strong proficiency in Python; comfort with Go, Rust, or Type Script is a plus
• Deep familiarity with cloud infrastructure (AWS, GCP, or Azure), Kubernetes, and infrastructure-as-code (Terraform or similar)
• Experience with vector databases, embedding pipelines, and retrieval systems
• Startup mindset: bias toward shipping, comfort with ambiguity, and willingness to work across the stack when needed
• Strong communication skills and the judgment to make pragmatic build-vs-buy tradeoffs

Nice to have:

• Experience as an early or founding engineer at a startup
• GPU cluster management, distributed training, or inference optimization (quantization, batching, caching)
• Experience with agent frameworks, tool use / function calling, and multi-modal systems
• Prior work in fast-moving product environments with direct customer exposure