Track Manager (Support & Operations) (IN)
HCLTech
HCLTech
Join our team as a Forward Deployment Engineer specializing in Generative AI and Agentic AI solutions 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, overseeing the entire process from technical discovery through production go-live and hypercare.
Your responsibilities will include significant software and integration ownership, executing customer deployment plans, and escalating architectural decisions when necessary. Expect to dedicate approximately 70% of your time to engineering and integration, 20% to customer interaction, and 10% to architecture contributions.
Collaborate directly with customer technical teams to grasp their application, infrastructure, data, integration, security, and operational needs, translating them into actionable solutions. Participate in technical discovery, solution workshops, demonstrations, proof-of-concepts, pilots, and deployment planning. Implement customer-specific Agentic AI solutions using Gemini Enterprise Agent Platform, ADK, Python, and frameworks like LangGraph and LangChain. Configure and customize agents, Skills, tools, workflows, RAG components, prompts, and enterprise connectors. Develop custom integrations using REST APIs, SDKs, MCP tools, databases, and ITSM platforms when standard connectors are unavailable. Set up customer endpoints, authentication, authorization, service accounts, IAM/RBAC, and security controls. Deploy and operate solutions on Google Cloud using services like Agent Runtime, Cloud Run, and GKE. Configure RAG and knowledge integrations, including data ingestion and access control. Implement logging, monitoring, tracing, and evaluation using Google Cloud capabilities. Execute various testing phases, including functional, integration, security, performance, and user acceptance testing. Troubleshoot production issues across agents, models, APIs, and cloud infrastructure, driving them to resolution. Analyze logs, traces, and evaluation results to implement corrective actions. Support CI/CD, environment promotion, versioning, releases, and production deployment activities. Optimize solutions for reliability, scalability, latency, usability, and cost. Document architecture, integrations, deployment steps, operational procedures, and support information. Conduct knowledge transfer to customer and internal teams, and support production hypercare. Provide feedback to development teams for platform improvements.
This role requires strong Python programming and software engineering fundamentals, coupled with hands-on experience in LLMs, RAG, prompt engineering, agentic workflows, and multi-agent systems. Proficiency with ADK and/or LangGraph/LangChain for production agent solutions is essential.
You should have hands-on experience with the Gemini Enterprise Agent Platform and Google Cloud AI services, along with robust REST API development and integration skills. A solid understanding of OAuth, API keys, IAM, RBAC, service accounts, and secrets management is necessary.
Experience with Google Cloud, particularly with production deployments using Cloud Run or GKE, is required. Familiarity with Git, CI/CD, Docker, and production deployment practices is also key. You'll need experience with logging, monitoring, tracing, debugging, and production incident troubleshooting. A good grasp of databases, SQL, enterprise data sources, RAG implementation patterns, and Responsible AI principles is important.
Excellent communication skills and the ability to engage directly with customer technical stakeholders are critical. Preferred qualifications include experience with Vertex AI, Cloud Observability, GenAI evaluation, Terraform, and various Google Cloud services like Pub/Sub and BigQuery. Experience with ITSM platforms and cloud operations is a plus.
HCLTech
IT Consulting