AI Engineer with Python

Location: Phoenix, AZ (Hybrid 3 days in office)

Python AI Engineer

-Knowledge Base Infrastructure

We are hiring a Python Platform Engineer to operate and evolve the infrastructure behind an enterprise knowledge base platform that is moving from a Confluence-focused RAG chatbot into a broader agentic knowledge system.

Today, the platform supports Confluence/GitHub ingestion → chunking → pgvector → RAG retrieval → FastAPI serving. Over the next phase, we are expanding toward hybrid retrieval (vector + sparse + graph), multi-source ingestion, evaluation pipelines, agent infrastructure, harness and shared chat platform primitives.

What You''ll Own:

·       Architect and implement backend services in Python 3.11, FastAPI, Pydantic, SQLAlchemy async, and asyncpg

·       Design retrieval and orchestration trade-offs around quality, latency, cost, safety, and operational simplicity

·       Build production-grade agent runtime capabilities: memory boundaries, tool sandboxing, permissions, and budget controls

·       Improve answer grounding, failure analysis, and citation enforcement rather than optimizing for demo behavior

·       Create observability and operational feedback loops with OpenTelemetry, PrometheGrafana, Docker/Helm, and GitHub Actions

·       Work closely with product and engineering partners to support multiple conversational surfaces through one knowledge platform

·       Ingestion infrastructure across current and future content sources

·       Observability across application, pipeline, database, and model-serving behavior

·       Cost, latency, throughput, and failure-mode management for AI-heavy workloads

·       Release workflows that validate AI behavior changes, not just code compilation

Qualifications:

·       Strong hands-on experience with Python in platform, automation, or infrastructure-heavy environments

·       Experience building CLI tools using Python, Golang or Rust.

·       Hands-on experience with LangGraph, LangChain, pgvector, and modern retrieval pipelines

·       Experience designing evaluation frameworks for LLM-backed systems, including regression detection and quality measurement

·       Strong experience with Docker, Helm, GitHub Actions, and Kubernetes-oriented workflows

·       Familiarity with the operational characteristics of embedding pipelines, vector search, and LLM-backed systems

·       Strong observability skills across metrics, tracing, dashboards, alerting, and log analysis

·       Experience with ingestion, ETL, or content-processing pipelines at scale

·       Ability to think in terms of reliability, cost, latency, throughput, and recovery

Nice to Have:

·       Experience with Qdrant, Neo4j, or other vector/graph infrastructure

·       Experience supporting RAG, search, evaluation, or agent platforms

·       Experience in enterprise or regulated environments

·       Familiarity with Vault, Splunk, Artifactory, ECR

·       Comfort using AI-assisted engineering workflows in day-to-day work