Sr Tower Lead (Support & Operations) (IN)
HCLTech
HCLTech
Advance your career as a Senior Forward Deployment Engineer (FDE) specializing in AWS Agentic AI. This role involves leading the technical architecture and end-to-end deployment of enterprise-grade Generative AI and Agentic AI solutions for key clients on AWS.
As a customer-facing solution architect with coding expertise, you will be instrumental in ensuring customer technical success. Your responsibilities will span architecture and deployment decisions, leading customer workshops, overseeing implementations, driving production readiness, and mentoring fellow FDEs. This is an opportunity to influence platform roadmaps and shape the future of AI solutions.
Own the complete technical delivery of enterprise Agentic AI deployments, from initial discovery and architecture to production rollout and ongoing support.
Lead critical customer interactions including technical workshops, architecture reviews, executive discussions, solution demonstrations, Proofs of Concept (POCs), and pilot programs.
Design sophisticated AI and AWS architectures leveraging Amazon Bedrock, AgentCore, and various AWS services, integrating with enterprise data, applications, and security controls.
Define detailed agent architectures, encompassing multi-agent patterns, skill integrations, RAG, human-in-the-loop mechanisms, state management, and enterprise connectivity.
Architect robust integration solutions for REST APIs, ITSM platforms, monitoring, identity systems, and proprietary applications.
Determine optimal implementation strategies, balancing configuration, custom extensions, and reusable platform capabilities.
Define production deployment architectures, ensuring high availability, scalability, security, and observability across Amazon Bedrock AgentCore components and core AWS services.
Lead security and identity architecture discussions, focusing on IAM, access controls, authentication, authorization, and network security.
Establish and review comprehensive production readiness criteria, covering all aspects from functionality and performance to governance and supportability.
Develop the customer AgentOps strategy, including telemetry, tracing, logging, metrics, evaluation, and cost monitoring.
Address complex production issues through expert troubleshooting and root-cause analysis involving agents, models, RAG, integrations, and AWS infrastructure.
Drive improvements in reliability, latency, scalability, model performance, and AI cost optimization for customer deployments.
Define and review CI/CD pipelines, release management processes, and deployment strategies.
Review FDE-produced deliverables, establishing and enforcing engineering quality standards.
Provide technical mentorship and guidance to FDEs and Associate FDEs.
Develop reusable deployment patterns, integration templates, reference architectures, and troubleshooting playbooks.
Identify recurring customer needs and collaborate with development teams to create reusable agents, tools, and platform capabilities.
Serve as the senior technical escalation point for critical customer issues.
Provide crucial technical feedback to product, engineering, security, and operations teams to influence platform roadmap priorities.
Lead technical handovers and customer enablement for seamless transition to support teams.
A strong foundation in Python and software engineering is essential, with the ability to guide production code quality.
Extensive hands-on experience with Generative AI, LLMs, RAG, prompt engineering, tool calling, evaluation, and multi-agent architectures is required.
Proven expertise with Amazon Bedrock and/or Amazon Bedrock AgentCore, preferably with frameworks like LangGraph or LangChain in production environments.
Significant hands-on experience in AWS architecture and engineering, covering Amazon Bedrock and fundamental AWS services.
Demonstrated experience in enterprise integration, including REST APIs, databases, ITSM platforms, monitoring, and identity systems.
A deep understanding of AWS IAM, role-based access, authentication, authorization, secrets management, and enterprise networking is crucial.
Strong experience with containerized applications (Docker, ECS/EKS), Lambda, AgentCore Runtime, and production deployment patterns.
Proficiency in CI/CD, Git, release management, versioning, and production operations.
Solid experience with observability, tracing, logging, monitoring, debugging, evaluation, and incident management.
A firm grasp of RAG architecture, knowledge integration, retrieval, evaluation, and agent quality measurement.
Experience with Responsible AI principles, guardrails, AI security, data protection, and enterprise governance.
Excellent customer-facing communication skills, with the ability to lead technical architecture discussions with senior stakeholders.
Bachelor’s or Master’s degree in Computer Science, Engineering, IT, or a related field, alongside 8-12 years of relevant technical experience, with at least 3 years dedicated to Generative AI/Agentic AI. A track record of successfully delivering enterprise technology or AI solutions into production, coupled with demonstrated customer-facing technical leadership, is expected.
HCLTech
IT Consulting