Lead Assistant Manager

Cloud AI Engineer

• Lead the end-to-end development cycle of AI applications, from conceptualization and prototyping to deployment and optimization, with a core focus on LLM-driven solutions.
• Architect and implement highly performant and scalable AI services, effectively integrating with GCP's comprehensive AI/ML ecosystem.
• Collaborate closely with product managers, data scientists, and MLOps engineers to translate complex business requirements into tangible, AI-powered features.
• Continuously research and apply the latest advancements in LLM technology, prompt engineering, and AI frameworks to enhance application capabilities and performance.
  

• Develop and deploy production-grade AI applications and microservices primarily using Python and FastAPI, ensuring robust API design, security, and scalability.
• Design and implement end-to-end LLM pipelines, encompassing data ingestion, processing, model inference, and output generation.
• Utilize Google Cloud Platform (GCP) services extensively, including Vertex AI (Generative AI, Model Garden, Workbench), Cloud Functions, Cloud Run, Cloud Storage, and BigQuery, to build, train, and deploy LLMs and AI models.
• Expertly apply prompt engineering techniques and strategies to optimize LLM responses, manage context windows, and reduce hallucinations.
• Implement and manage embeddings and vector stores for efficient information retrieval and Retrieval-Augmented Generation (RAG) patterns.
• Work with advanced LLM orchestration frameworks such as LangChain, LangGraph, Google ADK, and CrewAI to build sophisticated multi-agent systems and complex AI workflows.
• Integrate AI solutions with other enterprise systems and databases, ensuring seamless data flow and interoperability.
• Participate in code reviews, establish best practices for AI application development, and contribute to a culture of technical excellence.
• Keep abreast of the latest advancements in GCP AI/ML services and broader AI/ML technologies, evaluating and recommending new tools and approaches.
  

• Two or more years of hands-on experience as an AI Engineer with a focus on building and deploying AI applications, particularly those involving Large Language Models (LLMs).
• Strong programming proficiency in Python, with significant experience in developing web APIs using FastAPI.
• Demonstrable expertise with Google Cloud Platform (GCP), specifically with services like Vertex AI (Generative AI, AI Platform), Cloud Run/Functions, and Cloud Storage.
• Proven experience in prompt engineering, including advanced techniques like few-shot learning, chain-of-thought prompting, and instruction tuning.
• Practical knowledge and application of embeddings and vector stores for semantic search and RAG architectures.
• Hands-on experience with at least one major LLM orchestration framework (e.g., LangChain, LangGraph, CrewAI).
• Solid understanding of software engineering principles, including API design, data structures, algorithms, and testing methodologies.
• Experience with version control systems (Git) and CI/CD pipelines.
  

Preferred Skills And Qualifications

Good To Have