Description

Experience Required: 10+ years

JD:

-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, Prometheus/Grafana, 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

Key Skills

Education

Any Graduate