Applied AI Engineer (GenAI / RAG / Agentic AI / Azure)

Hot Opening: Applied AI Engineer (GenAI | RAG | Agentic AI | Azure)

Experience: 7-10 Years
Location: India (Remote)
Employment Type: Full Time
Role Level: MidSenior

Role Overview

We are looking for a passionate Applied AI Engineer who thrives on building real-world Generative AI solutions. This role goes beyond basic AI implementation and focuses on architecting enterprise-grade GenAI platforms, developing RAG pipelines, and designing agentic AI workflows.

You will work closely with AI leaders, Data teams, and Business stakeholders to transform business problems into secure, scalable, production-ready AI applications.

If you enjoy building with LLMs, LangChain ecosystems, vector databases, and cloud AI services, this is your opportunity to work on cutting-edge AI innovation.

Key Responsibilities

AI Platform Engineering

  • Design and develop scalable AI application components for enterprise AI platforms
  • Build agentic workflows, batch AI processing pipelines, and enterprise data integrations
  • Develop reusable GenAI services and modular AI architecture

RAG & Agentic AI Development

  • Build advanced RAG (Retrieval Augmented Generation) pipelines
  • Design embeddings, vector search strategies, and semantic retrieval systems
  • Implement multi-agent decision workflows using LangGraph or similar frameworks

API & Backend Development

  • Build high-performance backend services using Python and FastAPI
  • Develop secure APIs connecting LLMs with enterprise systems
  • Optimize model response performance, latency, and cost

LLM Integration & Orchestration

  • Integrate and orchestrate multiple LLM providers:
  • OpenAI
  • Anthropic Claude
  • Google Gemini
  • Implement model routing strategies based on use cases
  • Optimize prompts and AI workflows for accuracy and efficiency

Deployment & LLMOps

  • Deploy AI applications using CI/CD pipelines
  • Containerize solutions using Docker
  • Implement LLM monitoring (prompt drift, hallucination tracking, accuracy metrics)
  • Maintain AI observability and performance dashboards

Cloud & Data Engineering

  • Work with Azure AI Services and Azure Cloud
  • Design and optimize vector database schemas
  • Work with Azure AI Search, Pinecone, Milvus, PostgreSQL

Architecture & Collaboration

  • Partner with Program Managers and Business Analysts for feasibility analysis
  • Define AI architecture patterns for business use cases
  • Mentor junior engineers and review technical implementations

Required Skills

Primary Skills

  • Strong experience with LLM APIs (OpenAI, Claude, Gemini)
  • Advanced experience with LangChain
  • LangGraph
  • LlamaIndex
  • Strong Python development experience
  • FastAPI backend development experience
  • Experience building RAG pipelines and agentic AI systems

Technical Skills

  • Vector Databases (Azure AI Search, Pinecone, Milvus)
  • PostgreSQL or relational databases
  • Azure Cloud platform
  • Git version control
  • Docker & CI/CD pipelines

Good to Have

  • Node.js basic knowledge
  • LLM monitoring tools
  • Prompt engineering expertise
  • AI governance or Responsible AI exposure

What Makes You a Great Fit

  • Experience building production GenAI applications
  • Strong system design and AI architecture mindset
  • Experience working with enterprise AI platforms
  • Passion for emerging AI technologies
  • Strong problem solving and collaboration skills

Why Join Us?

  • Work on next-generation Generative AI platforms
  • Opportunity to build enterprise AI products
  • Exposure to cutting-edge AI tools and frameworks
  • High visibility role with architecture ownership
  • Collaborative AI innovation environment
Back to blog

Other Jobs To Apply

No other job posts for this day.