Senior Backend Engineer Generative AI

Location: Remote
Type: Project-Based Senior-Level
Domain: Generative AI LLMs RAG Systems Cloud-Scale APIs FastAPI
CLICK HERE TO DO THE INTERVIEW: Project Engagement Overview

• Scope: Develop the entire backend and AI-agent layer for a greenfield chatbot platform including chatbot services system architecture database and integrations.
• Compensation Model: Fixed-price contract between USD (final amount to be determined post-discovery).
• IP & Ownership: All source code documentation prompts and architecture artifacts will be the exclusive property of our company. The engineer may not reuse resell or share any part of the work without prior written permission.
• Warranty & Bug-Fix Period: Youll remain available for up to 3 months after project handoff to fix bugs or fill any functional gaps free of charge.

• Code should be clean maintainable and scalable adhering to best practices (e.g. SOLID principles DRY comprehensive README).
• Well conduct regular code reviews; feedback must be addressed promptly.

• Work closely with our Business Owner to understand the use case confirm requirements and align tech decisions with business goals.
• Collaborate continuously with our System Architect on system design and database structure; they may review your PRs and progress.
• Maintain close coordination with our Front-End engineer during development communication should be open and proactive.
• A DevOps engineer will assist around deployment time; expect cooperative handoff.
• Be available for 23 hours of timezone overlap with GMT3 (Palestine) for real-time discussions (exact hours TBD).

• Submit complete setup instructions environment configuration and API documentation (Swagger/OpenAPI or equivalent).
• Share entity-relationship diagrams (ERDs) and system architecture visuals using tools like Miro or Lucidchart.
• When needed record short Loom or screen-share walkthroughs to explain complex modules.

• Design and build robust secure and scalable APIs and microservices for LLM-powered applications using FastAPI.
• Develop modular RAG pipelines integrating vector databases (Milvus or Qdrant) with custom retrieval logic.
• Work with models like LLaMA Mistral GPT and embedding models (Nomic OpenAI HuggingFace).
• Optimize inference speed and memory usage for multi-modal and NLP-based systems running in production.
• Celery for task queues and monitoring (Flower Prometheus).
• Handle authentication & authorization with JWT OAuth and secure role-based access control (RBAC).
• Utilize Docker for the project.
• Bouns: Architect cloud-native AI backends on AWS/GCP/Azure leveraging services like S3 EC2 Lambda Secrets Manager and Docker.
• Bouns: Ensure observability and reliability with CI/CD pipelines (GitHub Actions).

• 5 years of backend experience in Python (FastAPI Framework).
• 2 years working in AI/ML-driven systems or products ideally with experience in LLM integration or RAG systems.
• Experience with Postgres and one of FastAPI ORM such as SQLAlchemy-Almbic.
• Experience with LangChain LangGraph libraries.
• Strong understanding of vector similarity search and vector store integrations.
• Solid experience with containerization (Docker) and orchestrating distributed systems.
• Familiarity with data serialization async programming rate limiting and secure API design.
• Excellent debugging documentation and system design skills.
• Bachelors or Masters in Computer Science AI or related field.