Generative AI Engineer

Techolution is seeking a highly skilled Generative AI Engineer - Agentic Systems to lead the design, development, and deployment of cutting-edge LLM-powered systems. In this role, you will own end-to-end RAG pipelines, build autonomous multi-agent systems, and leverage state-of-the-art models, with a strong preference for Google Gemini Enterprise and Google ADK, to deliver high-impact, scalable AI solutions. This position demands deep technical expertise, exceptional problem-solving abilities, strong system design skills, and effective cross-functional collaboration to achieve measurable business outcomes.

Key Responsibilities:

• Design and implement end-to-end Retrieval-Augmented Generation (RAG) pipelines, managing the entire lifecycle from architecture to production deployment, optimization, monitoring, and scaling to ensure reliability, efficiency, and business impact.
• Develop and orchestrate agentic workflows and multi-agent systems capable of autonomous operation, decision-making, and interaction with external APIs, databases, tools, and real-world environments.
• Utilize function calling, tool use, and integration patterns to connect LLMs with external systems, monitoring tools, and orchestration frameworks.
• Work hands-on with state-of-the-art LLMs including Google Gemini (preferred), OpenAI models, and Anthropic Claude.
• Demonstrate a thorough understanding of architectures such as Transformers and Mixture of Experts (MoE), along with emerging AI paradigms.
• Architect scalable AI deployments on cloud platforms (GCP preferred, with Azure and AWS also considered), employing Kubernetes, MLOps practices, CI/CD pipelines, and high-availability patterns.
• Collaborate with product, engineering, and business teams to ensure AI solutions are explainable, interpretable, reliable, and aligned with strategic business objectives.
• Apply robust problem-solving skills, including DSA, OOP, design patterns, and large-scale system design principles to address complex technical challenges.

Required Qualifications & Skills:

• Minimum 1 year of experience with state-of-the-art LLM models, including Google Gemini (strongly preferred), OpenAI, and Anthropic.
• High proficiency in Python, including web frameworks like FastAPI/Flask and distributed task queues such as Celery.
• Deep understanding of LLM architectures (Transformers, MoE, etc.) and generative AI techniques.
• Proven expertise in designing and building agentic workflows, multi-agent systems, autonomous decision-making agents, orchestration frameworks (e.g., LangGraph, CrewAI, or similar), function calling, and tool integration.
• End-to-end experience with RAG pipelines, encompassing chunking, embedding, retrieval, reranking, generation, evaluation, and production scaling.
• Experience deploying and scaling AI/ML workloads on cloud platforms (GCP preferred, with Azure and AWS also considered), utilizing Kubernetes, MLOps tools, and implementing monitoring and observability solutions.
• Solid foundation in DSA, OOP, design patterns, and system design for large-scale, production-grade systems.
• Excellent communication and comprehension skills, with the ability to collaborate cross-functionally and articulate complex AI concepts to non-technical stakeholders.

Preferred / Advanced (Teachable) Skills

• Prior hands-on experience with Google ADK (Agent Development Kit) and Gemini Enterprise for building, governing, and deploying custom AI agents.
• Familiarity with advanced agent frameworks, memory systems, planning/reasoning loops, and observability in agentic applications.
• Experience with enterprise-grade AI governance, safety, compliance, and explainability.