Senior Python Engineer

We are hiring aSenior Python Engineerto help drive the evolution of an enterprise knowledge base platform.

This platform is transitioning from a Confluence-focused RAG chatbot to a comprehensive agentic knowledge system. You will play a key role in expanding the platform’s capabilities, including hybrid retrieval, multi-source ingestion, evaluation pipelines, agent infrastructure, and shared chat platform primitives.

Responsibilities

• Architect and develop backend services using Python 3.11, FastAPI, Pydantic, SQLAlchemy async, and asyncpg
• Design retrieval and orchestration strategies that balance quality, latency, cost, safety, and operational simplicity
• Build robust agent runtime features such as memory boundaries, tool sandboxing, permissions, and budget controls
• Enhance answer grounding, failure analysis, and citation enforcement to improve reliability and accuracy
• Establish observability and operational feedback loops with OpenTelemetry, Prometheus, Grafana, Docker, Helm, and GitHub Actions
• Collaborate with product and engineering teams to support multiple conversational interfaces through a unified knowledge platform
• Develop ingestion infrastructure for current and future content sources
• Implement observability across application, pipeline, database, and model-serving layers
• Manage cost, latency, throughput, and failure modes for AI-intensive workloads
• Create release workflows that validate AI behavior changes beyond code compilation

Requirements

• Minimum 3 years of relevant professional experience in software engineering
• Extensive hands-on experience with Python in platform, automation, or infrastructure-focused environments
• Experience building command-line tools using Python, Golang, or Rust
• Practical knowledge of LangGraph, LangChain, pgvector, and modern retrieval pipelines
• Experience designing evaluation frameworks for LLM-powered systems, including regression detection and quality assessment
• Strong background with Docker, Helm, GitHub Actions, and Kubernetes-based workflows
• Understanding of embedding pipelines, vector search, and operational aspects of LLM-driven systems
• Advanced observability skills, including metrics, tracing, dashboards, alerting, and log analysis
• Experience with ingestion, ETL, or large-scale content-processing pipelines
• Ability to approach system design with considerations for reliability, cost, latency, throughput, and recovery
• Excellent oral and written communication skills in English at B2+ level or higher

Nice to Have

• Experience with FastAPI for building web APIs
• Familiarity with Grafana and Splunk for monitoring and log analysis
• Knowledge of Qdrant, Neo4j, or other vector and graph database infrastructure