AI Engineer II

Overview

AI Engineer II role at Generac focused on designing, building and deploying production-grade AI applications, RAG architectures and agentic automation for an energy technology company.

What you'll do

• Design and develop production-grade AI applications and RAG architectures leveraging structured and unstructured enterprise knowledge repositories.
• Architect, deploy and scale autonomous AI agents capable of multi-step reasoning, planning, tool execution and complex workflow automation.
• Implement multi-agent communication networks and agent-to-system integrations using modern frameworks and protocols (e.g., Model Context Protocol - MCP).
• Embed intelligent assistants, copilot features, microservices and APIs into modern web applications and industrial operations software.
• Build robust solutions on cloud platforms including Microsoft Azure (Azure AI Foundry, Azure OpenAI Service, Azure AI Search, Azure Machine Learning, Azure Functions, Azure Databricks) and Google Cloud (Vertex AI, Gemini Models, Document AI, BigQuery, AlloyDB AI, Cloud Run).
• Develop hands-on solutions using modern agentic frameworks and open-source models, including LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen, Claude Agent SDK, Hugging Face, MCP, Llama, Gemma and Mistral.
• Develop continuous integration/deployment (CI/CD) pipelines for testing, evaluating and monitoring live AI applications.
• Perform advanced prompt engineering, fine-tuning, latency reduction and domain-specific model evaluation.
• Implement enterprise best practices for AI observability, performance tuning, model accuracy and responsible AI governance.

What you'll need

• Bachelor's or master's degree in computer science, Artificial Intelligence, Data Science, Machine Learning, Software Engineering, or a related technical discipline.
• 3+ years of hands-on experience building and deploying AI, ML, NLP or Generative AI solutions.
• Demonstrated experience delivering at least one production-ready AI application, LLM-powered platform or agentic workflow into a live environment.
• Strong working knowledge of LLMs, Prompt Engineering, RAG architectures, Vector Databases and RESTful Microservices.
• Solid understanding of modern software engineering practices (Git, CI/CD, unit testing, containerization).
• Advanced proficiency in Python (required).
• Architectures: GenAI, LLMs, RAG, Agentic AI, Autonomous Workflows, Vector DBs.
• Cloud Platforms: Azure AI, GCP Vertex AI.
• Frameworks: LangGraph, LangChain, LlamaIndex, MCP, CrewAI, AutoGen, Databricks, Google-BigQuery.

Nice to have

• Hands-on experience developing AI assistants, enterprise copilots or autonomous multi-agent orchestration frameworks.
• Deep knowledge of LLMOps/MLOps, evaluation frameworks and AI monitoring/observability tools.
• Experience in manufacturing, energy, industrial IoT, field service or engineering operations domains.
• Familiarity with JavaScript/TypeScript, enterprise security standards or Model Context Protocol (MCP).
• Active open-source contributions, technical publications or patent filings in AI/ML.

Details

• Location: Pune, India.
• Occasional travel.
• Physical demands: regular talking, hearing and standing/walking; occasional lifting up to 25 pounds; frequent computer-based work.