Track Manager (Support & Operations) (IN)
HCLTech
HCLTech
Join our team as a Forward Deployment Engineer (FDE) specializing in Generative AI and Agentic AI solutions on AWS. This role involves designing, customizing, integrating, deploying, and troubleshooting complex AI systems for enterprise clients. As a hands-on, customer-facing engineer, you will transform platform capabilities into impactful customer solutions, guiding them from initial technical discovery through production go-live and hypercare.
You will be instrumental in driving customer implementations, owning software and integration aspects, and ensuring successful execution of deployment plans. Collaboration and technical decision-making will be key components of your daily activities.
Engage directly with customer technical teams to grasp their application, infrastructure, data, integration, security, and operational needs, translating these into actionable solutions.
Participate in critical technical discovery sessions, solution workshops, demonstrations, proof-of-concepts, pilots, and deployment planning.
Implement tailored Agentic AI solutions utilizing Amazon Bedrock, Amazon Bedrock AgentCore, Python, and relevant agent frameworks like LangGraph or LangChain.
Configure and adapt reusable agents, skills, tools, RAG components, prompts, and enterprise connectors to meet specific customer environments.
Develop custom integrations through REST APIs, AWS SDKs, and various enterprise systems when pre-built connectors are not available.
Manage customer endpoints, authentication, authorization, IAM policies, and other security configurations for seamless integration.
Deploy and operate customer solutions on AWS, leveraging services such as Bedrock AgentCore Runtime, Lambda, ECS, and API Gateway.
Configure RAG and knowledge integrations, including data ingestion and access control, using customer-approved services.
Implement comprehensive logging, monitoring, tracing, and evaluation systems using Amazon Bedrock AgentCore Observability and CloudWatch.
Execute thorough testing, including functional, integration, security, performance, and user acceptance testing prior to production rollout.
Troubleshoot and resolve production issues across the entire AI solution stack and AWS infrastructure, driving them to successful closure.
Analyze logs, traces, and metrics to identify patterns and implement corrective actions for performance and reliability improvements.
Support CI/CD pipelines, environment promotions, versioning, releases, and production deployment activities.
Optimize solutions for reliability, scalability, latency, usability, and AI inference cost.
Document customer architectures, integrations, deployment procedures, operational runbooks, and troubleshooting guides.
Conduct knowledge transfer sessions for customer teams and internal support staff, providing post-launch hypercare.
Provide feedback to development teams on recurring customer needs to enhance platform reusability and improvements.
A strong foundation in Python programming and software engineering principles is essential.
Demonstrated hands-on experience with Large Language Models (LLMs), Retrieval Augmented Generation (RAG), prompt engineering, agentic workflows, and multi-agent systems is required.
Proven experience with Amazon Bedrock and/or Amazon Bedrock AgentCore for production agent solutions is a must.
Proficiency in REST API development and integration, working with JSON, YAML, AWS SDKs, and enterprise APIs.
Solid understanding of AWS IAM, role-based access, OAuth, API keys, Secrets Manager, authentication, authorization, and secure service-to-service integration.
Hands-on experience with AWS, including at least one production deployment model using ECS, EKS, Lambda, or AgentCore Runtime.
Familiarity with Git, CI/CD, Docker, and best practices for production deployment.
Experience in logging, monitoring, tracing, debugging, and troubleshooting production incidents.
Good knowledge of databases, SQL, enterprise data sources, and common RAG implementation patterns.
A good understanding of Responsible AI principles, security, data protection, and enterprise deployment requirements is beneficial.
Excellent communication skills, with the ability to effectively interact with customer technical stakeholders.
While not mandatory, experience with specific Amazon Bedrock components, MCP, A2A, Terraform, various AWS services, ITSM platforms, and supporting customer engagements is preferred.
Bachelor’s or Master’s degree in Computer Science, Engineering, Information Technology, or a related field, coupled with 4-7 years of overall technical experience, including at least 2 years in Generative AI/Agentic AI, is required. You should also have demonstrated experience delivering an AI, automation, or cloud solution into production.
HCLTech
IT Consulting