phoenix
phoenixPhoenix - Your AI Assistant
Inactive session will be ended in 24 hours
End Session

AI focused Backend Engineer

  • Posted:
  • Proposals: 31
  • Remote
  • #4511757
  • Expired
Aurel H.Dhirendra K.Ibrahim K.Nisar Ahmed R.Muhammad Abdul H. + 26 others have already sent a proposal.
  • 3

Description

Experience Level: Expert
Senior AI-Focused Backend Engineer sought to design and build scalable, secure services powering AI applications. Responsibilities include developing APIs, integrating LLMs and AI services, implementing RAG pipelines with vector databases, managing prompt and model routing, creating async processing, and ensuring observability and reliability. Required: 5+ years backend experience, Python (FastAPI/Django/Flask), PostgreSQL, Redis, LLM APIs, embeddings, background jobs, cloud, Docker, CI/CD, testing, and strong technical communication.

New Proposal

Login to your account and send a proposal now to get this project.

Log in

Clarification Board Ask a Question

  • Umar F.

    Most recently built RAG pipelines, multi-agent orchestration layers, and AI-powered backend services for taskade.com, and docus.ai. Currently providing Level 2 backend support for omninode.ai, a multi-agent platform running on AWS.

    Would love to understand what you're building.
    Quick call?

  • VCONN P.

    Hi, we'd appreciate a few additional details:

    1. Are you building a brand-new AI platform or extending an existing application?

    2. Which LLM providers are you planning to support initially (OpenAI, Anthropic, Gemini, Azure OpenAI, self-hosted models, etc.)?

    3. Do you already have a preferred vector database, or would you like us to recommend one based on your use case?

    4. What types of documents or knowledge sources will be indexed in the RAG pipeline (PDFs, websites, databases, SharePoint, etc.)?

    5. Are there any latency, throughput, or scalability targets we should consider?

    6. Will user authentication, billing, or multi-tenancy be required?

    7. Is deployment planned for AWS, Azure, Google Cloud, or another hosting environment?

    Looking forward to your reply.

  • Naresh S.

    Hi Lowell,

    For the AI backend, are you looking to establish a shared model-routing and RAG foundation that can support multiple products and providers, or is the immediate priority building a specific production workflow where retrieval quality, async processing, and observability can be tuned around one core use case?

    Thanks,
    Naresh