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 hands-on customer implementation, where you'll design, customize, integrate, deploy, and troubleshoot complex AI systems. You will be instrumental in transforming platform capabilities into working customer solutions, overseeing the entire lifecycle from technical discovery to post-production support.
Your typical engagement will involve approximately 70% engineering and integration, 20% customer interaction, and 10% architectural contributions. This is an exciting opportunity to work at the forefront of AI innovation with a focus on production delivery within the AWS ecosystem.
Engage directly with customer technical teams to deeply understand application, infrastructure, data, integration, security, and operational needs, translating these into actionable solutions. Participate actively in technical discovery sessions, solution workshops, and proof-of-concept activities. Implement custom Agentic AI solutions using Amazon Bedrock and relevant frameworks like LangGraph or LangChain.
Configure and adapt reusable agents, skills, and RAG components for specific customer environments. Develop bespoke integrations via REST APIs and AWS SDKs when standard connectors are insufficient. Securely configure endpoints, authentication, and authorization mechanisms within AWS. Deploy and manage customer solutions on AWS, leveraging services like Bedrock AgentCore Runtime, Lambda, and ECS/EKS.
Set up customer-specific RAG and knowledge integrations, ensuring robust data ingestion and retrieval. Implement comprehensive monitoring, logging, and evaluation strategies. Conduct thorough testing, including functional, integration, security, and performance tests, prior to production rollout. Troubleshoot and resolve production issues across the AI stack and AWS infrastructure, driving them to a successful conclusion.
Analyze performance metrics and logs to implement performance and cost optimizations. Support CI/CD pipelines and production deployment processes. Document architectures, integrations, and operational procedures. Conduct knowledge transfer sessions and provide hypercare support. Contribute feedback to platform engineering for continuous improvement.
A strong foundation in Python programming and software engineering is essential, coupled with hands-on experience in LLMs, RAG, prompt engineering, and agentic workflows. Proven experience with Amazon Bedrock and/or Amazon Bedrock AgentCore for production agent solutions is required.
Demonstrated expertise in REST API development and integration, working comfortably with JSON, YAML, AWS SDKs, and enterprise APIs. Solid understanding of AWS IAM, role-based access, OAuth, and secure service-to-service integrations is crucial. Experience with at least one AWS production deployment model using ECS, EKS, or Lambda is necessary.
Proficiency with Git, CI/CD practices, and Docker is expected. Experience in logging, monitoring, tracing, debugging, and production incident troubleshooting is vital. A good grasp of databases, SQL, enterprise data sources, and RAG implementation patterns is beneficial. Familiarity with Responsible AI principles, security, and enterprise deployment requirements is important. Excellent communication skills to effectively collaborate with customer stakeholders are a must.
While not mandatory, experience with specific AWS services like Bedrock AgentCore Runtime, Gateway, and Memory, as well as tools like Terraform or ServiceNow, will be advantageous. A Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field, combined with 4-7 years of overall technical experience (with at least 2 years in Generative AI/Agentic AI), is required.
HCLTech
IT Consulting