Track Lead (Support & Operations)

Gautam Buddha Nagar, Uttar Pradesh

Job Summary

Forward Deployment Engineer – GCP Agentic AI

Job Type

Full-Time

Experience

4–7 years overall; at least 2 years in Generative AI / Agentic AI with production delivery on Google Cloud

Locations

Noida, Hyderabad, Chennai, Bangalore, Pune

Primary Focus

Customer-specific engineering, integrations, deployment, productionization and troubleshooting

Role Overview

We are looking for a Forward Deployment Engineer (FDE) to design, customize, integrate, deploy, troubleshoot, and operationalize enterprise Generative AI and Agentic AI solutions for customers on Google Cloud. The FDE is a hands-on customer-facing engineer who turns reusable platform capabilities into working customer solutions and owns the implementation from technical discovery through production go-live and hypercare.

- Hands-on customer implementation engineer
- Heavy software and integration ownership
- Executes the customer deployment plan
- Escalates architecture/platform decisions when required

Typical time allocation

- ~70% engineering and integration
- ~20% customer interaction
- ~10% architecture contribution

Key Responsibilities

- Work directly with customer technical teams to understand application, infrastructure, data, integration, security, and operational requirements and translate them into implementable solutions.
- Participate in technical discovery sessions, solution workshops, demonstrations, proof-of-concepts, pilots, deployment planning, and go-live activities.
- Implement customer-specific Agentic AI solutions using Gemini Enterprise Agent Platform, ADK, Python, and appropriate agent frameworks such as LangGraph and LangChain.
- Configure and customize reusable agents, Skills, tools, workflows, RAG components, prompts, and enterprise connectors for customer environments.
- Develop customer-specific integrations using REST APIs, SDKs, MCP tools, databases, ITSM platforms, monitoring systems, identity services, and proprietary applications when reusable connectors are unavailable.
- Configure customer endpoints, authentication, authorization, OAuth/API credentials, service accounts, IAM/RBAC, Secret Manager, and other security controls required for integration.




- Deploy and operate customer solutions on Google Cloud using services such as Agent Runtime, Cloud Run, GKE, Cloud Functions, Pub/Sub, Cloud Storage, and related services.
- Configure customer-specific RAG and knowledge integrations, including data ingestion, retrieval, access control, and validation.
- Implement logging, tracing, metrics, monitoring, evaluation, and operational dashboards using Google Cloud capabilities and OpenTelemetry-based telemetry.
- Execute functional, integration, security, performance, resiliency, evaluation, and user acceptance testing before production rollout.
- Troubleshoot production issues across agents, models, prompts, tools, APIs, RAG, authentication, networking, and cloud infrastructure; drive issues to closure.
- Analyze logs, traces, metrics, evaluation results, latency, token usage, and failure patterns and implement corrective actions.
- Support CI/CD, environment promotion, versioning, releases, rollback, and production deployment activities.
- Optimize solutions for reliability, scalability, latency, usability, and AI inference cost.
- Document customer architecture, integrations, configuration, deployment steps, operational runbooks, troubleshooting procedures, and support information.
- Conduct knowledge transfer to customer teams and internal support/BAU teams and support production hypercare.
- Identify recurring customer requirements and provide structured feedback to Agent Development / Platform Engineering teams for reusable platform improvements.

Skill Requirements

Must Have Skills

- Strong Python programming and software engineering fundamentals.
- Hands-on experience with LLMs, RAG, prompt engineering, agentic workflows, tool/function calling, structured outputs, and multi-agent systems.
- Hands-on experience with ADK and/or LangGraph/LangChain for production agent solutions.




- Experience with Gemini Enterprise Agent Platform / Google Cloud AI services.
- Strong REST API development and integration experience; comfortable working with JSON, YAML, SDKs, and enterprise APIs.
- Working knowledge of OAuth, API keys, IAM, RBAC, service accounts, secrets management, authentication, and authorization.
- Hands-on experience with Google Cloud and at least one production deployment model using Cloud Run or GKE.
- Experience with Git, CI/CD, Docker, and production deployment practices.
- Experience with logging, monitoring, tracing, debugging, and production incident troubleshooting.
- Good understanding of databases, SQL, enterprise data sources, and RAG implementation patterns.
- Good understanding of Responsible AI, security, data protection, and enterprise deployment requirements.
- Strong communication skills and ability to work directly with customer technical stakeholders.

Preferred Skills

- Experience with Gemini models, ADK, Agent Runtime, Vertex AI / Gemini Enterprise Agent Platform services, Cloud Observability, and GenAI evaluation.
- Experience with MCP and enterprise tool integration.
- Experience with Terraform / Infrastructure-as-Code.
- Experience with GKE, Pub/Sub, BigQuery, Cloud Storage, Secret Manager, networking, and private connectivity.
- Experience with ServiceNow or other ITSM platforms and IT infrastructure / CloudOps / SRE / AIOps use cases.
- Experience supporting customer POCs, pilots, MVPs, production rollouts, and technical workshops.

Other Requirements

Qualifications

- Bachelor’s or Master’s degree in Computer Science, Engineering, Information Technology, or related field.
- 4–7 years of overall software engineering, cloud engineering, or equivalent technical experience.
- At least 2 years of practical Generative AI / Agentic AI experience.
- Demonstrated experience delivering an AI, automation, or cloud solution into production.

Key Attributes

- Customer-oriented and comfortable working in customer environments.
- Robust ownership and bias for execution.
- Strong troubleshooting and problem-solving ability.
- Able to balance reusable platform capabilities with customer-specific requirements.
- Comfortable working across AI engineering, cloud, integration, and operations.

📌 Track Lead (Support & Operations) (India)
🏢 HCLTech
📍 India