AI Knowledge Graph Engineer (Backend, ML, AWS)

We’re building an AI-powered knowledge graph platform that transforms unstructured documents into structured, query able intelligence. We have a defined ontology, a working prototype, and a clear roadmap. Now we’re hiring an engineer who can take this foundation and turn it into a scalable, production-grade system. This role is ideal for someone who enjoys building end-to-end data and ML systems, working with LLMs, and designing clean, reliable backend pipelines. What You’ll Work On You will own the development of a complete AI-driven knowledge acquisition workflow, including: ● Batch ingestion of documents and data from public sources ● Text parsing and normalization for downstream ML tasks ● Multi-pass LLM extraction pipelines (entities, events, relationships) ● Normalization/resolution of extracted data into structured, ontology-aligned objects ● Integration of human-in-the-loop review workflows and LLM Finetuning to improve extraction accuracy over time ● Construction and maintenance of the knowledge graph (AWS Neptune / Neo4j) ● Backend services and APIs that make the graph queryable What You’ll Bring We’re looking for someone with hands-on experience in several of the following areas: ● Graph databases (AWS Neptune, Neo4j, or similar) ● Knowledge graph construction or ontology-driven data systems ● LLM-based extraction (prompting, multi-pass pipelines, structured extraction) ● LLM fine-tuning or distillation (improve model efficiency) ● Deploying AI/ML workloads on AWS (SageMaker, Bedrock) ● Backend engineering in Python (Pydantic, structured data modeling, ETL frameworks) ● Web scraping or automated document ingestion (Proxies, Crawl4Ai, Scrapling) ● Familiarity with AWS cloud infrastructure, observability, and CI/CD Who You Are ● You’re a strong backend engineer with an interest in LLMs and structured knowledge systems. ● You enjoy designing multi-step pipelines and understanding how data moves end to end. ● You’re pragmatic — you choose what works best, whether that’s fine-tuned models, external services, or standard AWS components. ● You like refining schemas and ontologies when new patterns emerge. ● You care about reliability, versioning, and not breaking production systems. ● You’re comfortable being the primary owner of a sophisticated backend/ML pipeline. Nice to Haves ● Experience modeling temporal events or lifecycle chains ● Prior work with ontology evolution or schema refinement ● Insights into building human-in-the-loop review cycles ● Interest in improving extraction accuracy through ML techniques over time Why This Role Is Interesting ● You’ll be the first engineer shaping a system that turns messy, real-world documents into structured intelligence. ● You’ll work with a founder who already built a working prototype and a detailed ontology. ● The system is technically deep: LLMs, graph databases, ETL, AWS cloud, and structured knowledge representation. ● Plenty of room to grow into an architect-level role as the platform scales.