Track Manager (Support & Operations) (IN)
HCLTech
HCLTech
Seeking a Forward Deployment Engineer specializing in Generative AI and Agentic AI on Google Cloud. This hands-on, customer-facing role involves designing, customizing, integrating, deploying, and troubleshooting enterprise AI solutions. You will transform platform capabilities into working customer implementations, owning the process from technical discovery through production go-live and hypercare. A significant portion of your time will be dedicated to engineering and integration.
This position focuses on customer-specific engineering, integrations, deployment, productionization, and ongoing troubleshooting. You will be instrumental in ensuring successful adoption and operation of advanced AI solutions within client environments.
Collaborate closely with customer technical teams to define application, infrastructure, data, integration, security, and operational needs. Participate in comprehensive technical discovery sessions, solution workshops, and proof-of-concepts. Implement customer-specific Agentic AI solutions using Gemini Enterprise Agent Platform, ADK, and frameworks like LangGraph/LangChain. Configure and customize agents, tools, workflows, RAG components, and enterprise connectors. Develop custom integrations via REST APIs, SDKs, and other enterprise systems when standard connectors are unavailable. Securely configure customer endpoints, authentication, and authorization mechanisms.
Deploy and operate solutions on Google Cloud, leveraging services like Agent Runtime, Cloud Run, and GKE. Implement robust RAG and knowledge integrations, focusing on data ingestion, retrieval, and access control. Establish comprehensive logging, monitoring, and evaluation systems using Google Cloud capabilities. Execute thorough testing, including functional, integration, security, and performance testing, prior to production rollout. Troubleshoot and resolve production issues across various components, driving them to closure. Analyze performance data to optimize solutions for reliability, scalability, latency, and cost-effectiveness. Document architecture, configurations, deployment procedures, and operational runbooks. Conduct knowledge transfer sessions and provide support during production hypercare. Provide structured feedback to engineering teams to enhance platform capabilities based on recurring customer requirements.
A strong foundation in Python programming and software engineering is essential, complemented by hands-on experience with LLMs, RAG, prompt engineering, and agentic workflows. Proficiency with ADK or LangGraph/LangChain for production agent solutions is required. Experience with the Gemini Enterprise Agent Platform and Google Cloud AI services is crucial. You should possess robust REST API development and integration skills, coupled with a working knowledge of security protocols like OAuth and IAM. Hands-on experience with Google Cloud, including production deployments on Cloud Run or GKE, is necessary. Familiarity with CI/CD, Docker, production deployment practices, and debugging is expected. A solid understanding of databases, SQL, and RAG implementation patterns is beneficial, as is awareness of Responsible AI principles and enterprise deployment requirements.
This role demands excellent communication skills and the ability to engage effectively with customer technical stakeholders. While a Bachelor’s or Master’s degree in a related field is preferred, significant practical experience in Generative AI/Agentic AI and delivering AI, automation, or cloud solutions into production is highly valued. The ideal candidate is customer-oriented, possesses strong ownership and execution drive, and excels at problem-solving while balancing platform reusability with specific customer needs. Comfort working across AI engineering, cloud, integration, and operations domains is key.
HCLTech
IT Consulting