SDE II / Founding Engineer

About the role The first engineer we hire. You own the architecture, write the code, take it to production, and lead the engineering team as it grows. Software engineering and applied AI in equal measure. Key responsibilitiesArchitectureOwn the end-to-end system design: platform, web, mobile, data, securityMake build, buy and integrate decisions across every layerDefine the technical standards the team works toData and retrievalBuild ingestion pipelines for structured and unstructured enterprise dataDesign hybrid retrieval across vector, keyword and metadata searchImplement knowledge graphs and persistent memoryAI systemsDesign multi-agent architectures with supervisor and sub-agent patternsBuild orchestration, tool calling, state management and human-in-the-loopOwn fine-tuning pipelines, adapter versioning and model routingEvaluation and observabilityBuild the eval harness before any fine-tuning beginsImplement tracing, cost and latency tracking, drift and regression alertsOwn accuracy, grounding and hallucination detectionProductionTake the platform to production and keep it thereOwn infrastructure, deployment, CI/CD, monitoring and securitySupport cloud, on-premise and air-gapped deploymentDelivery and teamTranslate the product roadmap into working softwareSet delivery cadence, quality gates and engineering standardsHire, onboard and lead the engineering teamTechnologiesYou will not have used all of these. You should be strong across most, and able to pick up the rest. Languages: Python, TypeScript, SQL Backend: FastAPI, Node.js, REST, gRPC, async services Frontend and apps: Next.js, React, React Native Generative AI: LangChain, LangGraph, MCP, A2A, Claude, OpenAI, open-source models (Llama, Mistral, Qwen) Agent orchestration: Multi-agent supervisor patterns, task decomposition, tool and function calling, parallel sub-agents, state management, human-in-the-loop, agent and skill registries, CrewAI, Google ADK Workflow orchestration: Airflow, Celery, event-driven pipelines, scheduled jobs, retry and fallback logic Retrieval: Vector databases, embeddings, hybrid and semantic search, GraphRAG, knowledge graphs Fine-tuning: LoRA, QLoRA, PEFT, adapter versioning, model distillation ML and data: PyTorch, Spark, Kafka, Delta Lake, ETL and streaming pipelines MLOps and evaluation: MLflow, LangFuse, LangSmith, W&B, Portkey, experiment tracking, eval harnesses, LLM-as-judge, drift detection, model routing and fallback Databases: PostgreSQL, MongoDB, Redis, Elasticsearch, Neo4j Cloud: AWS, Azure or GCP Infrastructure: Docker, Kubernetes, Helm, Terraform, GitHub Actions, CI/CD Observability: Prometheus, Grafana, OpenTelemetry Required experienceBuilt and shipped an enterprise-grade AI or platform product end to end in productionDeep hands-on experience with agent frameworks, orchestration and tool callingRAG in production: vector search, embeddings, hybrid retrieval, evaluationFine-tuning and model operations: dataset curation, training, benchmarkingStrong backend, API, data and cloud engineering. Hands on, not architecture onlyContainers, orchestration, CI/CD, observability and securityEvaluation as a discipline: eval sets, LLM-as-judge, hallucination detection, driftPreferredFounding or first engineering hire at an early-stage companyExperience building from nothing rather than inheriting an existing systemTrack record shipping under real business constraints and fixed timelinesWhat success looks likeThe platform is live, in production, with real usersReleases ship on cadence and quality holdsThe evaluation framework tells us whether each change helpedThe engineering team grows and does its best work