Artificial Intelligence Engineer

Role & responsibilities

• Lead the implementation of

  Retrieval-Augmented Generation (RAG)

  pipelines that combine LLMs with real-time data from customer environments.
• Integrate

  Azure OpenAI

  services and develop optimized prompt strategies for scalable use across our iPaaS platform.
• Implement and manage

  vector databases

  such as

  Milvus

  ,

  FAISS

  ,

  Pinecone

  , or

  Azure Cognitive Search

  to support contextual retrieval and semantic search.
• Build intelligent

  AI agents

  using frameworks like LangChain or Semantic Kernel that can perform step-by-step automation across integration workflows.
• Collaborate with product and UX teams to embed AI in user-centric ways that simplify complexity and improve customer outcomes.
• Ensure scalable and reliable deployments through best practices in

  Docker

  ,

  Kubernetes

  , and

  CI/CD pipelines

  .

Preferred candidate profile

• 5-8 years of experience in AI/ML engineering, including production systems.
• Strong experience with

  LLMs

  ,

  prompt engineering

  , and designing AI features.
• Proven track record building and deploying

  RAG pipelines

  and using

  vector search

  effectively.
• Experience with

  vector databases

  like

  Milvus

  ,

  FAISS

  ,

  Pinecone

  , or

  Azure Cognitive Search

  .
• Hands-on experience with

  Azure OpenAI

  , including GPT models and embedding APIs.
• Experience developing

  AI Agents

  with LangChain or Semantic Kernel.
• Solid Python skills and familiarity with Hugging Face Transformers.
• Background in

  natural language processing (NLP)

  ,

  unstructured data processing

  , or

  knowledge graph development

  .
• Proficiency in containerization (

  Docker

  ,

  Kubernetes

  ) and CI/CD for scalable deployments.