Artificial Intelligence Specialist

AI Engineering & Infrastructure Lead (GCP)

Role Overview

We are seeking a highly experienced AI Engineering & Infrastructure Lead (GCP) to architect, build, and scale enterprise-grade AI applications. This role requires deep expertise across the full AI stack from data and knowledge modeling to retrieval systems, orchestration frameworks, infrastructure, observability, and cost optimization.

This is not a prompt engineering or chatbot POC role. We are looking for a hands-on leader who has successfully implemented production-ready, enterprise decisioning systems, leveraging advanced RAG architectures, knowledge graphs, and cloud-native AI infrastructure.

Key Responsibilities

• Architect and build scalable AI applications on Google Cloud Platform
• Design and implement advanced RAG architectures, including GraphRAG
• Develop and optimize Knowledge Graph solutions using graph databases (preferably Neo4j)
• Model ontologies and design graph schemas for enterprise use cases
• Implement and optimize Vector Database solutions for performance, scalability, and cost efficiency
• Lead orchestration and observability using the LangChain ecosystem
• Establish guardrails, monitoring, and governance mechanisms for AI systems
• Optimize LLM inference performance and cost
• Implement security, access control, and enterprise-grade compliance standards
• Mentor engineering teams and define best practices for AI infrastructure.

Required Skills & Expertise

• Knowledge Graphs & Graph Databases
• Hands-on development experience with Neo4j (preferred) or similar graph databases
• Performance tuning and query optimization experience
• Strong understanding of ontologies, semantic modeling, and entity relationships

RAG & Advanced AI Architectures

• Deep understanding of various RAG architectures
• Experience implementing advanced constructs such as GraphRAG
• Strong grasp of hybrid retrieval strategies

Vector Database Expertise

• Expert-level knowledge of at least one Vector DB (Pinecone, Weaviate, Milvus, etc.)
• Index tuning (HNSW or equivalent)
• Embedding optimization
• Cost-performance tradeoff management

Orchestration & Observability

• Production experience with LangChain or related frameworks
• Experience implementing observability, tracing, and debugging AI workflows
• Guardrail implementation and hallucination mitigation strategies

GCP AI/ML Stack

• Strong experience with Vertex AI and other GCP AI services
• Experience with GKE, Cloud Run, BigQuery, IAM, and cloud-native deployment models
• Infrastructure as Code and CI/CD for AI workloads