Lead development of production AI systems for building-system design including vision pipelines for PDF/CAD parsing, LLM+RAG workflows for code-compliant designs, AI agent orchestration, and full-stack features across a Typescript/React/Node/Postgres platform. Significant ownership and technical direction at an early-stage startup.
About Semble AI
Semble AI builds AI agents that design building-systems (fire, HVAC, plumbing, and security). Construction companies use Semble to replace weeks of manual design work with instant, code-compliant system layouts and bills of materials.
The $600B building-system integration industry still runs on spreadsheets and hand-drawn markups, even as building codes evolve rapidly and grow more localized. It’s one of the largest blind spots in construction tech, and we’re fixing it.
Jonathan and Ethan met studying computer science at Stanford. Jonathan worked at Convergint, one of the world’s largest building-system integrators, to learn the industry from the inside. Ethan’s motivation is personal: his home burned down in 2017 due to a faulty fire system.
We’re building the platform that will become the industry standard for construction-system design, and we’re looking for people who want to build foundational AI products that touch every building on the planet.
As a founding engineer, you’ll work directly with the founders to own and build systems such as:
- Vision pipelines that segment rooms, walls, and architectural elements from noisy PDFs/CAD files
- LLM + RAG workflows that interpret building codes and produce compliant designs
- Full-stack features across our React/Node/Postgres platform
You’ll have massive ownership and help set the technical direction of a company in a market that’s about to undergo a once-in-a-generation transition.
- Typescript / React / Node / Express / PostgreSQL
- Python (PyTorch, NumPy, etc.)
- Vision models: object detection, instance + semantic segmentation
- AI Agents: multi-agent reasoning, workflow orchestration, MCP
- RAG pipelines: vector DBs, embeddings, chunking strategies
- Have strong experience in ML (vision AND LLMs), backend, building AI agents, and full-stack engineering
- Thrive in fast-moving environments and love shipping end-to-end
- Care about building reliable, production-grade AI systems
- Want to be early at a YC startup where your work directly defines the company’s trajectory
- You’ll work directly with the founding team (YC F25)
- Ship real AI systems into production for companies across the U.S.
- Own major pieces of the product and architecture
- Help shape the engineering culture from day zero
- Build something that will become the industry standard for top quality commercial building design
The base pay range for this role is $150,000 – $250,000 per year.
Similar Jobs
Angel or VC Firm • Artificial Intelligence
Design, build, and operate end-to-end training and inference infrastructure for large language and multimodal models. Improve efficiency (memory, parallelism, kernel optimizations), ensure robust scalable training and RL pipelines, optimize low-latency/high-throughput serving (quantization, caching, speculative decoding), manage multi-GPU and multi-cloud orchestration, and productionize new algorithms with strong observability and reproducibility.
Top Skills:
C++CachingCudaDeepspeedFeature StoresFlashattentionGoGrafanaKubernetesMegatronOpentelemetryPrometheusPulumiPythonPyTorchQuantizationRayRustSglangSpeculative DecodingTerraformTgiTritonVector DatabasesVllm
Artificial Intelligence • Software • Industrial • Manufacturing
Design, train, evaluate, and optimize agent-native LLMs and RAG pipelines for enterprise use. Build training and RL pipelines (RLHF/DPO/PPO), embedding-based memory, evaluation harnesses, observability, and inference optimization across cloud and on-prem environments.
Top Skills:
ChromaCohereDeepspeedDelta LakeDuckdbDustFaissFalconFlashattentionFsdpHuggingface TransformersIcebergJavaScriptJinaKubernetesLambdalabsLangchainLanggraphLangsmithLlama 3LlamaindexLoraMistralMixtralModalNeo4JOpenllm EvalsOwlParquetPineconePostgresPuppygraphPythonQdrantQloraRagasRayRdfRustSagemakerTgiTrulensVllmWeaviateWeights & Biases
Artificial Intelligence • Software • Industrial • Manufacturing
Build and operate secure, scalable ML pipelines and hybrid GPU infrastructure for training, fine-tuning, serving, and governing open-source LLMs and agentic apps. Implement CI/CD, model versioning, observability, benchmarking, security controls, and integration with RAG/agent tools and vector DBs to support production deployments across tenants.
Top Skills:
AirflowArgocdBashChromaDagsterDeepspeedDockerDvcEksFaissFsdpGithub ActionsGkeGrafanaHelmHuggingface HubHuggingface InferenceHuggingface TrainerKeycloakKubernetesLambdaLangchainLanggraphLangsmithLlamaindexMlflowModalOpaOpenllm-EvalsOpentelemetryPrefectPrometheusPythonQdrantQloraRagasRayRay ServeRegoSagemakerTerraformTgiTriton Inference ServerVaultVllmWeaviateWeights & Biases
What you need to know about the San Francisco Tech Scene
San Francisco and the surrounding Bay Area attracts more startup funding than any other region in the world. Home to Stanford University and UC Berkeley, leading VC firms and several of the world’s most valuable companies, the Bay Area is the place to go for anyone looking to make it big in the tech industry. That said, San Francisco has a lot to offer beyond technology thanks to a thriving art and music scene, excellent food and a short drive to several of the country’s most beautiful recreational areas.
Key Facts About San Francisco Tech
- Number of Tech Workers: 365,500; 13.9% of overall workforce (2024 CompTIA survey)
- Major Tech Employers: Google, Apple, Salesforce, Meta
- Key Industries: Artificial intelligence, cloud computing, fintech, consumer technology, software
- Funding Landscape: $50.5 billion in venture capital funding in 2024 (Pitchbook)
- Notable Investors: Sequoia Capital, Andreessen Horowitz, Bessemer Venture Partners, Greylock Partners, Khosla Ventures, Kleiner Perkins
- Research Centers and Universities: Stanford University; University of California, Berkeley; University of San Francisco; Santa Clara University; Ames Research Center; Center for AI Safety; California Institute for Regenerative Medicine
