Track Lead (Support & Operations) (IN)
HCLTech
HCLTech
Join us as a Forward Deployment Engineer (FDE) focused on Generative AI and Agentic AI solutions within the Google Cloud ecosystem. This role involves designing, customizing, integrating, and operationalizing cutting-edge AI applications for enterprise clients. You will be a key hands-on engineer, transforming platform capabilities into tangible customer solutions, guiding them from initial discovery through production deployment and ongoing support.
This position emphasizes direct customer engagement and extensive ownership of software and integration aspects. The FDE plays a critical role in executing customer deployment plans and escalating complex architecture or platform decisions as needed. Expect a dynamic role with approximately 70% dedicated to engineering and integration, 20% customer interaction, and 10% architectural contributions.
Collaborate closely with customer technical teams to deeply understand their application, infrastructure, data, integration, security, and operational needs, translating these into actionable solutions. Participate in crucial technical discovery sessions, solution workshops, demonstrations, proof-of-concepts, pilots, and comprehensive deployment planning. Implement bespoke Agentic AI solutions using the Gemini Enterprise Agent Platform, ADK, Python, and leading agent frameworks like LangGraph and LangChain. Configure and tailor reusable agents, Skills, tools, workflows, RAG components, prompts, and enterprise connectors to meet specific customer environments. Develop custom integrations leveraging REST APIs, SDKs, MCP tools, databases, ITSM platforms, monitoring systems, and identity services where standard connectors are insufficient. Securely configure customer endpoints, authentication, authorization, OAuth/API credentials, service accounts, IAM/RBAC, Secret Manager, and other essential security controls. Deploy and manage customer solutions on Google Cloud using services such as Agent Runtime, Cloud Run, GKE, Cloud Functions, Pub/Sub, and Cloud Storage. Set up customer-specific RAG and knowledge integrations, overseeing data ingestion, retrieval, access control, and validation processes. Implement robust logging, tracing, metrics, monitoring, evaluation, and operational dashboards using Google Cloud capabilities and OpenTelemetry. Execute comprehensive testing, including functional, integration, security, performance, resiliency, evaluation, and user acceptance testing prior to production rollout. Proactively troubleshoot production issues across agents, models, prompts, tools, APIs, RAG, authentication, networking, and cloud infrastructure, driving them to swift resolution. Analyze logs, traces, metrics, evaluation results, latency, token usage, and failure patterns to implement effective corrective actions. Support CI/CD pipelines, environment promotion, versioning, releases, rollbacks, and production deployment activities. Optimize solutions for peak reliability, scalability, low latency, usability, and cost-effectiveness in AI inference. Create detailed documentation for customer architecture, integrations, configuration, deployment procedures, operational runbooks, and troubleshooting guides. Conduct knowledge transfer sessions to customer teams and internal support/BAU teams, providing hypercare support post-production. Identify recurring customer needs and channel structured feedback to Agent Development and Platform Engineering teams to enhance platform reusability.
Core technical skills include strong Python programming and robust software engineering fundamentals. Proven hands-on experience with LLMs, RAG, prompt engineering, agentic workflows, tool/function calling, structured outputs, and multi-agent systems is essential. Demonstrate practical expertise with ADK and/or LangGraph/LangChain for production agent solutions, alongside hands-on experience with the Gemini Enterprise Agent Platform and other Google Cloud AI services. A solid background in REST API development and integration, comfortable working with JSON, YAML, SDKs, and various enterprise APIs, is required. Familiarity with OAuth, API keys, IAM, RBAC, service accounts, secrets management, and authentication/authorization protocols is expected. Possess hands-on experience with Google Cloud, including at least one production deployment using Cloud Run or GKE. Proficiency with Git, CI/CD practices, Docker, and standard production deployment methodologies is necessary. Experience in logging, monitoring, tracing, debugging, and resolving production incidents is key. A good understanding of databases, SQL, enterprise data sources, and RAG implementation patterns is beneficial. Familiarity with Responsible AI principles, security best practices, data protection, and enterprise deployment requirements is important. Excellent communication skills are vital for effectively engaging with customer technical stakeholders.
HCLTech
IT Consulting