Python AI Engineer

Quick Facts

• Role: Python AI Engineer

• Focus: Production-grade AI infrastructure for an enterprise knowledge base platform

• Evolution: From Confluence-focused RAG to hybrid retrieval and agentic knowledge systems

Description

You will architect and implement backend services and pipelines in Python 3.11 to power enterprise retrieval and conversational experiences. The platform will expand from current Confluence/GitHub ingestion, chunking, pgvector storage, RAG retrieval, and FastAPI serving into hybrid retrieval (vector + sparse + graph), multi-source ingestion, agent infrastructure, and robust evaluation. Emphasis is on scalable, reliable, and production-ready AI infrastructure rather than demo behavior.

Responsibilities

• Architect and implement robust backend services using Python 3.11, FastAPI, Pydantic, SQLAlchemy async, and asyncpg

• Design trade-offs for retrieval quality, latency, cost, safety, and operational simplicity

• Build production-grade agent runtime capabilities (memory boundaries, tool sandboxing, permissions, budget controls)

• Improve answer grounding, failure analysis, and citation enforcement

• Create observability and operational feedback loops with OpenTelemetry, Prometheus/Grafana, Docker/Helm, and GitHub Actions

• Own ingestion infrastructure across current and future content sources

• Manage cost, latency, throughput, and failure-mode operations for AI-heavy workloads

• Build release workflows that validate AI behavior changes

• Partner with product and engineering teams to support multiple conversational surfaces via a unified knowledge platform

Requirements

• Strong, hands-on Python experience 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

• Ability to design evaluation frameworks for LLM-backed systems (regression detection and quality measurement)

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

• Familiarity with embedding pipelines, vector search, and LLM-backed systems

• Strong skills in metrics, tracing, dashboards, alerting, and log analysis

• Experience with ingestion/ETL/content-processing pipelines at scale

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

Benefits

Not specified in the provided posting.