AI Engineer

Role Overview

As an AI Engineer at AI Intime, you will contribute to building and scaling production-grade AI systems for enterprise use cases. You will work on knowledge retrieval, agent orchestration, multimodal AI, and system integrations, helping transform research ideas into real-world AI products.

You will play a key role in designing AI systems that directly impact how enterprises access, understand, and act on knowledge.

This role offers hands-on exposure to modern Generative AI systems, including on-prem LLMs, agentic frameworks, tool-based architectures, and multimodal pipelines.

Key Responsibilities

• Build and enhance RAG and Agentic AI pipelines
• Develop AI services and APIs using Python
• Work with on-prem model runtimes and orchestration layers
• Design agent workflows for intent classification, planning, and tool usage
• Integrate enterprise data sources and tools via connectors
• Support speech and multimodal AI pipelines (STT/TTS)
• Work with vector and graph-based retrieval systems
• Collaborate with product and engineering teams to ship production AI

Required Skills & Qualifications

Must Have

• 0–2 years of experience (or strong academic/personal projects)
• Strong programming skills in Python
• Understanding of Machine Learning, NLP, and LLM concepts
• Working knowledge of:
  • Relational & NoSQL databases (MySQL, MongoDB)
  • Redis or similar systems
  • Vector databases
  • Embeddings and similarity search

Good to Have

• Exposure to:
  • Model serving frameworks (vLLM, Ollama, or similar)
  • RAG or Agentic AI systems
  • Tool-based or MCP-style architectures
  • Agentic development using Google ADK framework (or similar)
• Experience with:
  • STT / TTS systems
  • Multimodal AI pipelines
• Familiarity with:
  • Linux
  • Docker
  • On-prem deployments