Solution Architect (DFS) (IN)
HCLTech
HCLTech
Join our team as a Senior Forward Deployment Engineer, focusing on AWS Agentic AI. This role involves leading the technical architecture and full deployment of enterprise Generative AI and Agentic AI solutions for key clients on AWS. You will act as a customer-facing solution architect with coding capabilities, driving technical success, making critical architecture and deployment decisions, and guiding FDEs.
This position offers a dynamic mix of responsibilities, approximately 50% dedicated to architecture and technical leadership, 30% to customer engagement, and 20% to engineering oversight and mentorship. You will play a pivotal role in shaping the future of AI solutions for our enterprise clients.
Take ownership of the end-to-end technical delivery of enterprise Agentic AI deployments, from initial discovery and architecture through production rollout and ongoing support. Lead crucial customer interactions including discovery sessions, technical workshops, architecture reviews, and executive discussions. Design robust AI and AWS architectures utilizing Amazon Bedrock, AgentCore, and various AWS services, integrating with enterprise data sources, applications, and security controls.
Define detailed agent architectures, including multi-agent patterns, Planner/Critic/Supervisor designs, domain agents, RAG, and human-in-the-loop controls. Establish integration architectures for REST APIs, databases, ITSM platforms, and other critical enterprise systems. Determine the optimal implementation path for requirements, whether through configuration, custom extensions, or platform capabilities. Define comprehensive production deployment architectures, encompassing availability, scalability, security, observability, and disaster recovery.
Lead discussions on security and identity architecture, ensuring adherence to IAM, role-based access, and data protection best practices. Define and review production readiness criteria across functionality, performance, reliability, and governance. Develop the customer AgentOps strategy, focusing on telemetry, tracing, logging, and operational dashboards. Manage complex troubleshooting and root-cause analysis for production issues. Drive improvements in reliability, latency, scalability, model performance, and AI cost optimization. Define and oversee CI/CD, release management, and deployment processes.
Review code, deployment plans, and technical deliverables from FDEs, maintaining high engineering quality standards. Mentor and guide FDEs and Associate FDEs. Establish reusable deployment patterns, reference architectures, runbooks, and troubleshooting playbooks. Identify and drive the conversion of recurring customer requirements into reusable agents and platform capabilities. Serve as the senior technical escalation point for complex customer issues and production incidents. Provide valuable technical feedback to product and engineering teams, influencing the platform roadmap.
We seek individuals with strong Python and software engineering expertise, capable of guiding production code. Extensive hands-on experience with Generative AI, LLMs, RAG, prompt engineering, tool calling, evaluation, and multi-agent architectures is essential.
Demonstrated proficiency with Amazon Bedrock and/or Amazon Bedrock AgentCore, alongside frameworks like LangGraph or LangChain in production environments. Solid AWS architecture and engineering experience across Amazon Bedrock and core AWS services is required. Significant enterprise integration experience with REST APIs, databases, ITSM platforms, monitoring systems, and identity platforms is a must.
A deep understanding of AWS IAM, role-based access, OAuth, secrets management, authentication, authorization, security, and enterprise networking is crucial. Experience with containerized applications (Docker, ECS/EKS, Lambda), production deployment patterns, CI/CD, Git, release management, versioning, and production operations is expected.
Strong experience in observability, tracing, logging, monitoring, debugging, evaluation, and production incident management. A thorough understanding of RAG architecture, knowledge integration, retrieval, evaluation, and agent quality measurement is vital. Familiarity with Responsible AI, guardrails, AI security, data protection, and enterprise governance is also required.
Candidates must possess strong customer-facing communication skills and the ability to lead architecture conversations with senior technical stakeholders. A Bachelor's or Master's degree in Computer Science, Engineering, Information Technology, or a related field is required, alongside 8-12 years of overall technical experience, with at least 3 years focused on Generative AI/Agentic AI. A proven track record of delivering enterprise AI solutions into production and demonstrated customer-facing technical leadership are essential.
HCLTech
IT Consulting