AI Engineer

About the Role

AI Engineer is the builder of UpGenie's core. You own the AI layer of a production system that answers high-stakes questions about rights, law, and safety. Our system retrieves across tens of thousands of jurisdictions and multiple legal domains, reasons over structured metadata like eligibility thresholds and enforcement agencies, validates its own sources, and proves its accuracy through evals. You will work on retrieval quality, schema design, evaluation infrastructure, and the roadmap from today's pipeline to a genuinely agentic system. You will ship to production from your first weeks, with real users and real partners depending on what you build.

Key Responsibilities

• Retrieval quality: Own the RAG architecture end to end, including chunking, metadata filtering, ranking and re-ranking, and the retrieval logic.
• Schema and metadata layer: Design the structured data that makes legal knowledge machine-usable, including thresholds, agencies, citations, and jurisdiction hierarchies.
• Evals as infrastructure: Build the evaluation framework that proves answer quality, including hallucination traps, citation validation, cascade-logic tests, and statistically defensible coverage claims.
• Source validation: Own the AI-first pipeline that decides which legal sources enter the system and which are rejected, and make its failure modes visible.
• Agentic roadmap: Move the system from hard-coded workflow logic to schema-aware prompting and tool-using agents.

Requirements & Tech Stack

• You ship working code: Production systems you built, not notebooks.
• Fluency in Python.
• Comfort owning a service that real users hit.
• Strong AI fundamentals: Understanding of retrieval, embeddings, context management, prompting, and evaluation at the level of mechanisms.
• Rigor: Test before claiming, measure before optimizing, and flag uncertainty.
• High agency: Ability to unblock yourself, scope ambiguous problems, propose approaches, and build.
• Range: Ability to move across retrieval, data pipelines, prompting, and evaluation, and learn new tools quickly.
• Clear communicator: Ability to explain technical concepts to non-technical partners and defend design decisions.

Even Better If

• Shipped RAG or LLM systems in production.
• Experience with Vertex AI, GCP, or comparable cloud AI stacks.
• Built evaluation or testing infrastructure for AI systems.
• Worked with legal, regulated, or otherwise high-stakes data.
• Public work examples (open source, writing, side projects).