IIQ - AI Engineer

Design, develop, and deploy enterprise-scale Generative AI solutions using LLMs, SLMs, and multimodal models. • Build advanced Retrieval-Augmented Generation (RAG) systems, including hybrid search, re ranking, context management, and knowledge-grounded generation. • Develop Agentic AI solutions capable of planning, reasoning, tool usage, workflow orchestration, and multi-agent collaboration. • Design and implement MCP (Model Context Protocol) based architectures, including MCP servers, tools, and enterprise integrations. • Fine-tune, evaluate, and optimize foundation models and SLMs for domain-specific use cases. • Build scalable, secure, and production-ready AI applications following software engineering best practices. • Implement LLMOps/MLOps practices including evaluation, observability, monitoring, governance, prompt management, and model lifecycle management. • Deploy AI solutions on AWS, Azure, or GCP using modern cloud-native architectures. • Collaborate with business stakeholders, architects, and global teams to translate business challenges into AI-driven solutions. • Stay current with emerging AI technologies, frameworks, and research.

Required Skills & Experience • 5–7 years of software engineering experience with at least 3+ years focused on AI/ML or Generative AI. • Strong programming skills in Python with expertise in building scalable backend services and APIs. • Hands-on experience with: o RAG architectures and vector databases o Agentic AI frameworks and multi-agent systems o MCP (Model Context Protocol) implementations o Prompt engineering, evaluation frameworks, and AI guardrails o LLMs such as OpenAI, Claude, Gemini, Llama, Mistral, or similar • Experience with frameworks such as LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen, Semantic Kernel, OpenAI Agents SDK, or PydanticAI. • Strong understanding of data structures, algorithms, system design, distributed systems, and software architecture. • Experience with Docker, Kubernetes, CI/CD, and cloud platforms (AWS, Azure, or GCP). • Familiarity with LLMOps/MLOps, observability, and evaluation tools such as LangSmith, MLflow, Promptfoo, DeepEval, Ragas, or similar.

AI-Assisted Engineering (Must Have) • Demonstrated ability to effectively use AI-powered development tools such as Cursor, Claude Code, GitHub Copilot, Windsurf, Cline, Aider, Codex, or similar. • Experience building AI-native development workflows for code generation, debugging, testing, refactoring, documentation, and productivity enhancement. • Exposure to engineering platforms and CI/CD tools such as Harness, GitHub Actions, Azure DevOps, Jenkins, or GitLab CI/CD.