Alex Beattie

Forward Deployed Engineer at McKinsey & Company. AI engineer, founder of KiNDD.

Forward Deployed Engineer at McKinsey & Company, building production LLM and agent systems on a QuantumBlack life sciences engagement. Previously Agentic AI Software Engineer at Technia and sole AI and backend engineer at Ourself Health.

I work across the parts of AI engineering that determine whether a system survives production: request routing, grounding, source metadata, streaming contracts, eval harnesses, observability, model routing, and cloud cost controls.

Core Focus

  • Production AI systems: routing, tool selection, safety gates, Strands agent behavior, and observable decision flows
  • RAG and retrieval: pgvector, Pinecone, Cohere embeddings, source metadata, query rewriting, grounding, and retrieval evaluation
  • LLM evaluation: Langfuse traces, gold-case evals, LLM-as-judge workflows, deterministic retrieval metrics, and live trace scoring
  • Model economics: cost-aware routing, token analytics, budget alerts, and smaller-model paths for simple queries
  • Backend architecture: Django, Python, Strawberry GraphQL, PostgreSQL, Redis, and API contracts
  • Cloud infrastructure: AWS Bedrock, ECS, Aurora, S3, GitHub Actions, and production cost optimization
  • Mobile-connected systems: Flutter clients, streaming APIs, auth flows, and mobile/backend contracts
  • AI development workflows: Cursor custom rules/skills, Claude Code, MCP servers, and IDE-native engineering context

Selected Projects

  • KiNDD Resource Navigator - nonprofit app I founded for families navigating developmental disability services in LA County. Live web map, iOS app on the App Store, Django/PostGIS backend, Bedrock AI assistance.
  • Anthropic AI for Science grant - software engineer on a UCLA and Dup15q Alliance team using Claude to characterize clinical features and trajectories in a rare neurodevelopmental disorder (announcement).
  • Unified Connectors MCP Server - MCP-first engineering workflow layer for GitHub, Slack, Jira, Confluence, Google Docs, and Miro.

KiNDD writing:

Experience

I have 14+ years of experience shipping software across mobile, backend, cloud, and AI systems. Current role: Forward Deployed Engineer at McKinsey & Company (QuantumBlack life sciences). Before that: Agentic AI Software Engineer at Technia, Senior Full-Stack Engineer and sole AI engineer at Ourself Health, and contract Full-Stack Engineer at Children’s Hospital Los Angeles, where KiNDD began. My work moved from Swift/iOS and TypeScript/Node.js into Python-first backend and AI infrastructure.

Before healthcare AI, I spent 13 years as the sole technologist for a real estate firm, owning software, automation, web systems, integrations, and technical operations end to end.