Description

Design and scale async REST/WebSocket APIs with Python and FastAPI, implementing multi-agent workflows and RAG systems.

This role is on-site.

Responsibilities

• Build async REST/WebSocket APIs using Python 3.11+, FastAPI, and vertical-slice architecture.
• Implement multi-agent workflows with Semantic Kernel to route traffic among specialised LLM agents.
• Deliver Retrieval-Augmented Generation (RAG) using vector stores like Azure AI Search, pgvector, or Chroma.
• Maintain CI/CD pipelines with Bitbucket Jenkins, including linting, testing, Docker packaging, and deployment.
• Instrument services with OpenTelemetry and structlog to monitor cost, latency, and p95 performance.

Required Skills

• 5+ years building production APIs in Python; 2+ years with FastAPI or similar async stacks.
• Deep knowledge of async I/O, Pydantic v2, dependency injection, and observability.
• Hands-on experience with Semantic Kernel or comparable agent frameworks.
• Practical RAG implementations using Azure AI Search, pgvector, or Chroma.
• Strong Postgres skills, including SQLModel/SQLAlchemy 2 and Alembic migrations.
• Proven integrations with LLM APIs (OpenAI, Gemini) and structured-output design.
• Dependency management via Poetry and end-to-end CI/CD ownership.

Preferred Skills

• Experience with event/message queues such as RabbitMQ, Azure Service Bus, or Kafka.
• Familiarity with observability stacks like Grafana or LangFuse for LLM cost governance.

Key Skills

Education

Any Graduate