AI Engineer

As an AI Engineer at Innover, you will play a crucial role in building next-generation AI applications leveraging Generative AI and Agentic AI systems. Your primary focus will be designing and developing AI-powered applications using LLMs for various use cases like summarization, Q&A, document parsing, and chatbots. Additionally, you will be responsible for orchestrating agentic workflows, implementing retrieval-augmented generation pipelines, translating business problems into AI workflows, collaborating with clients, deploying production-grade AI solutions, and developing scalable APIs and microservices around AI capabilities. Key Responsibilities: - Design and build GenAI-powered applications using LLMs for use cases like summarization, Q&A, document parsing, and chatbots. - Orchestrate agentic workflows using frameworks like LangChain, LangGraph, Semantic Kernel, autogen, etc. - Implement retrieval-augmented generation (RAG) pipelines using vector stores and embedding models. - Translate business problems into AI workflows involving multi-agent planning, decision-making, and task execution. - Collaborate closely with clients to prototype, build, test, and deploy products powered by GenAI/LLM technology on a large scale. - Deploy and maintain production-grade AI solutions using MLOps practices, including model monitoring, versioning, and CI/CD pipelines. - Develop scalable, modular APIs and microservices around AI capabilities. - Collaborate closely with data scientists, ML engineers, and product teams to iterate and refine models. Qualifications Required: - 2+ years of experience in Data Science, Applied AI, or AI Engineering roles. - Hands-on experience working with LLMs and GenAI models via APIs or fine-tuning. - Experience building and deploying agent-based AI systems using tools like LangGraph, LangChain Agents, or Semantic Kernel Planners. - Strong proficiency in Python and experience with common AI/ML frameworks. - 2+ years of experience with AWS, GCP, or Microsoft Azure. - Experience building microservices with Azure Functions and/or AWS Lambda functions. - 1+ years" experience with MLOps, CI/CD pipeline development, containerization, model deployment in test and production environments. - Experience in AI/ML technologies and software engineering. - At least 2+ years of hands-on experience with Python and 1+ years of experience building and maintaining scalable API solutions. Nice to have Skills: - Familiarity with multi-agent systems, workflow planners, or autonomous agents. - Exposure to LangGraph node/edge orchestration, OpenAI function calling, or tools/plugins. - Experience with structured information extraction from unstructured documents. - Understanding of AI safety, guardrails, or trustworthy AI principles.,