Senior AI Engineer

About Veaver

At Veaver, we are building the world’s most intelligent legal knowledge infrastructure — combining verified legal data with cutting-edge AI to make laws, judgments, and regulations easier for everyone to understand.

If you want to work where AI meets real-world impact, you’ll feel at home here.

Role Overview

We are looking for a Senior AI Engineer with deep hands-on experience in Google Cloud Platform, Firebase Console, Vertex AI, vector search, and Retrieval-Augmented Generation (RAG) systems.

This role is for someone who has built AI systems end-to-end, scaled them in production, and understands both the engineering and research sides of applied LLMs.

You will own the architecture, implementation, and optimization of the AI foundation powering Veaver.

Key Responsibilities

AI Engineering & RAG Architecture

• Architect and scale RAG pipelines for legal search, reasoning, and summarization.
• Build and optimize embedding generation, chunking strategies, document retrieval, and model orchestration.
• Implement evaluation systems for hallucination reduction, accuracy scoring, and content coverage.
• Experiment with LLMs, embeddings, and prompt strategies.

Google Cloud Platform & Vertex AI

• Lead development of AI workloads on Vertex AI (embeddings, tuning, pipelines, deployments).
• Build automated training, inference, and evaluation environments.
• Ensure cost optimization, reliability, and performance across GCP services.

Firebase & Backend Architecture

• Manage Firestore, Auth, Cloud Functions, and Storage.
• Build Node.js or Python backend APIs for AI features.
• Ensure scalability, logging, monitoring, and CI/CD pipelines.

Data Pipelines & Legal Knowledge Preparation

• Design ingestion pipelines for acts, rules, judgments, and notifications.
• Build automated flows for parsing, cleaning, and vectorizing legal content.
• Work with researchers to convert legal text into structured metadata.

Cross-Functional Collaboration

• Work closely with Product, Research, and Founders on AI-powered experiences.
• Translate legal domain knowledge into ML-ready datasets.
• Mentor junior engineers and influence the AI roadmap.

Ideal Candidate Profile

• 5–10 years experience in AI/ML engineering, NLP, or cloud-based backend systems.
• Strong expertise in Vertex AI, GCP, and Firebase Console.
• Experience building RAG systems, vector search, or LLM-powered products.
• Deep knowledge of Python, Node.js, embeddings, and ML pipelines.
• Experience with Weaviate, Pinecone, FAISS, or Milvus.
• Understanding of deployment, evaluation metrics, and LLM guardrails.
• Bonus: experience with legal, regulatory, financial, or long-document domains.

Why Join Veaver

• Build AI systems that solve meaningful, real-world problems.
• Architect the core intelligence powering Veaver’s legal knowledge engine.
• Work directly with founders in a high-ownership environment.
• Freedom to innovate and shape the AI roadmap.
• Competitive salary + ESOPs for experienced candidates.