Track Manager (Support & Operations) (IN)
HCLTech
HCLTech
Seeking a Forward Deployment Engineer specializing in Generative AI and Agentic AI solutions on Google Cloud. This role focuses on customer-specific engineering, integrations, deployment, and production support. You will be instrumental in transforming platform capabilities into working solutions, guiding customers from technical discovery through production go-live and hypercare.
This is a hands-on, customer-facing position requiring significant ownership of software and integration efforts. You'll actively execute customer deployment plans and escalate critical architecture decisions when necessary. The role typically involves approximately 70% engineering and integration, 20% customer interaction, and 10% architectural contribution.
Collaborate closely with customer technical teams to define application, infrastructure, data, integration, security, and operational needs, translating them into actionable solutions. Engage in technical discovery, solution workshops, demonstrations, proofs-of-concept, pilots, and deployment planning. Implement customized Agentic AI solutions using Gemini Enterprise Agent Platform, ADK, Python, and frameworks like LangGraph and LangChain. Configure reusable agents, skills, workflows, RAG components, prompts, and enterprise connectors. Develop custom integrations via REST APIs, SDKs, MCP tools, databases, and ITSM platforms when standard connectors are insufficient. Secure customer endpoints, authentication, authorization, and cloud infrastructure using IAM/RBAC and Secret Manager. Deploy and manage solutions on Google Cloud leveraging services like Agent Runtime, Cloud Run, and GKE. Set up RAG and knowledge integrations, including data ingestion and access control. Implement comprehensive logging, monitoring, and evaluation using Google Cloud capabilities and OpenTelemetry. Conduct thorough testing, including functional, integration, security, and performance testing. Troubleshoot and resolve production issues across various components and drive them to closure. Analyze performance data and logs to implement corrective actions. Support CI/CD pipelines, environment promotions, and production deployments. Optimize solutions for reliability, scalability, latency, and cost. Document architecture, integrations, deployment procedures, and operational runbooks. Provide knowledge transfer to customer and internal teams, supporting production hypercare. Provide feedback to platform engineering for continuous improvement.
Requires a strong foundation in Python programming and software engineering principles. Must possess hands-on experience with LLMs, RAG, prompt engineering, agentic workflows, and multi-agent systems, specifically using ADK or LangGraph/LangChain for production agent solutions. Proficiency with Gemini Enterprise Agent Platform and Google Cloud AI services is essential. Demonstrated experience with REST API development, integration, and working with JSON, YAML, and SDKs is required. A solid understanding of OAuth, API keys, IAM, RBAC, service accounts, and secrets management is necessary. Candidates must have hands-on Google Cloud experience, including at least one production deployment using Cloud Run or GKE. Familiarity with Git, CI/CD, Docker, and production deployment practices is expected. Experience in logging, monitoring, tracing, debugging, and production incident troubleshooting is crucial. A good understanding of databases, SQL, enterprise data sources, and RAG implementation patterns is needed, alongside knowledge of Responsible AI, security, and enterprise deployment requirements. Excellent communication skills for direct engagement with customer technical stakeholders are mandatory. A Bachelor's or Master's degree in Computer Science, Engineering, or a related field, along with 4-7 years of overall technical experience (including at least 2 years in Generative AI / Agentic AI), is required. Proven experience delivering an AI, automation, or cloud solution into production is a must.
HCLTech
IT Consulting