Senior AI Backend Engineer – Remote

About the role

We are looking for a Senior AI Backend Engineer to design and deliver high‑performance, AI‑powered backend services that power our client solutions. You will work remotely, collaborating with product and data teams to build scalable APIs, integrate multiple large‑language‑model providers, and ensure reliable, cost‑effective AI processing at scale.

Key responsibilities

• Integrate and manage multiple AI providers (LLMs, image/video generation) with smart fallback and cost‑optimization strategies.
• Design and optimize prompt‑engineering pipelines for consistent, high‑quality outputs.
• Develop high‑throughput REST and GraphQL APIs using Django and FastAPI with async processing.
• Implement real‑time features via Server‑Sent Events, WebSockets, and background workers (Celery).
• Architect micro‑services with robust error handling, rate limiting, monitoring, and observability.
• Optimize database queries, implement caching, and design efficient data models.
• Build Retrieval‑Augmented Generation (RAG) pipelines and vector‑embedding solutions.
• Write comprehensive tests, maintain CI/CD pipelines, and conduct code reviews.

Required profile

• 5+ years of professional software engineering experience.
• Strong production experience with Python, Django and/or FastAPI, and async programming (asyncio, async/await).
• Hands‑on experience integrating LLM APIs (OpenAI, Gemini, etc.) and optimizing token usage.
• Deep knowledge of PostgreSQL, Redis, and message brokers (RabbitMQ, SQS).
• Proficiency with Docker, Git, cloud platforms (AWS or GCP), and CI/CD workflows.
• Experience building scalable micro‑services, RESTful and GraphQL APIs, and real‑time communication (SSE/WebSockets).

Required skills

• Python
• Django
• FastAPI
• asyncio / async‑await
• OpenAI, Gemini APIs
• Prompt engineering
• PostgreSQL
• Redis
• Celery
• RabbitMQ / SQS
• Docker
• Git
• AWS / GCP
• CI/CD pipelines
• REST
• GraphQL
• Authentication & rate limiting
• SSE & WebSockets
• Pinecone / Weaviate / pgvector
• RAG architectures
• MongoDB / NoSQL
• Temporal / Airflow
• Kubernetes
• Datadog / Sentry / ELK
• LangChain / LlamaIndex