Senior AI Backend Engineer

TL;DR

Senior AI Backend Engineer (AI): Design and scale async REST/WebSocket APIs with Python/FastAPI and implement multi-agent workflows using Semantic Kernel to integrate LLM providers and RAG systems. Focus on evolving Postgres schemas, maintaining CI/CD pipelines, and instrumenting services for low-latency observability under high concurrency.

Location: Remote (Canada) with daily overlap of at least 09:00–13:00 EST

Salary: $90,000–$130,000 annually

Company

Original digital identity authority securing domain names, protecting brands, and safeguarding online infrastructure with AI-accelerated tools for millions of users.

What you will do

• Design and scale async REST/WebSocket APIs using Python 3.11+, FastAPI, dependency-injection, type hints, and vertical-slice architecture.
• Implement multi-agent workflows with Semantic Kernel for handoff, sequential, and concurrent routing among specialized LLM agents.
• Integrate LLM providers like OpenAI GPT-4.1/mini and Google Gemini 2.5 Flash behind a provider-agnostic layer for A/B and cost-aware routing.
• Deliver Retrieval-Augmented Generation with vector stores such as Azure AI Search, pgvector, or Chroma.
• Expose tool-using agents via OpenAI Assistants for data-analysis and file-manipulation tasks.
• Evolve schemas with SQLModel/SQLAlchemy 2 and Alembic; tune Postgres for high-concurrency async access; maintain CI/CD with Bitbucket Jenkins.
• Instrument services with structlog JSON logs, OpenTelemetry traces, and metrics to hold p95 latency under 100 ms.

Requirements

• 5+ years building production APIs in Python; 2+ years with FastAPI or similar async stack
• 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; end-to-end CI/CD ownership
• Excellent analytical and problem-solving ability
• Remote work readiness with daily overlap of at least 09:00–13:00 EST

Nice to have

• Event/message queues (RabbitMQ, Azure Service Bus, Kafka)
• Observability stacks (Grafana, LangFuse) for LLM cost governance

Culture & Benefits

• Work-life balance with thrilling, meaningful work
• Culture of diversity, inclusion, and belonging with 20+ affinity groups
• Competitive HMO benefits (175k MBL with one free dependent after one year), punctuality bonus, generous vacation policy
• Learning and development opportunities, career growth, mentoring