AI Engineer

Company Description Giggso, founded in 2017 in Michigan, helps enterprises navigate complex digital transformation challenges with a strong focus on AI deployment at scale. As a certified Minority Business Enterprise (MBE), the company brings diverse perspectives to solving governance and engineering problems for Fortune 500 clients worldwide. Giggso specializes in moving organizations from experimental AI pilots to profitable AI initiatives grounded in robust governance. The firm is built around the intersection of Governance, Risk, Compliance (GRC) and engineering, turning AI governance from a bottleneck into a competitive advantage. More information about Giggso and its work can be found at www.giggso.com.

Role Description his is a full-time, on-site AI Engineer role supporting enterprise AI initiatives aligned with governance, security, and compliance standards. The AI Engineer will design, develop, and deploy production-grade Generative AI solutions using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI frameworks. The role involves building scalable AI applications, integrating AI services with enterprise systems, optimizing model performance, and ensuring responsible AI practices throughout the development lifecycle. The AI Engineer will collaborate with cross-functional teams to translate business requirements into innovative AI solutions while contributing to Giggso's AI engineering standards, frameworks, and best practices.

Key Responsibilities

• Design and develop LLM-based applications using OpenAI, Azure OpenAI, and open-source models such as LLaMA and Mistral.
• Implement prompt engineering, model fine-tuning, embedding generation, and LLM evaluation frameworks to improve AI solution performance and accuracy.
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking, retrieval, reranking, and response generation.
• Design and develop Agentic AI solutions using LangChain, LangGraph, AutoGen, and CrewAI.
• Implement multi-agent orchestration, tool integration, memory management, agent routing, and autonomous workflow execution.
• Design, configure, and manage vector databases such as Pinecone, Chroma, and Azure AI Search.
• Develop embedding indexing, similarity search, hybrid retrieval, and vector search optimization strategies.
• Integrate AI services with enterprise applications, APIs, databases, and knowledge repositories.
• Monitor, evaluate, and optimize AI application performance, reliability, and governance in production environments.
• Collaborate with Data Engineers, Platform Engineers, Architects, and business stakeholders to deliver scalable AI solutions.

Required Skills

• 5+ years of experience in AI/ML Engineering, Generative AI, or Applied AI development.
• Hands-on experience with OpenAI, Azure OpenAI, and open-source LLMs (LLaMA, Mistral, etc.).
• Strong expertise in Prompt Engineering, RAG Architecture, Embeddings, and LLM Evaluation.
• Experience with LangChain, LangGraph, AutoGen, CrewAI, and agent orchestration frameworks.
• Hands-on experience with Pinecone, Chroma, Azure AI Search, or similar vector databases.
• Proficiency in Python, REST APIs, and AI application development.
• Understanding of AI governance, security, responsible AI, and production deployment best practices.
• Strong analytical, problem-solving, and communication skills.

Work Location & Hours

• Work Mode: Full-time, Work From Office (Mandatory)
• Location: Chennai, Gurugram, or Pune
• Work Hours: USA Pacific Standard Time (PST) business hours