Track Manager (Support & Operations) (IN)
HCLTech
HCLTech
Join our team as a Forward Deployment Engineer (FDE) to architect, customize, and implement cutting-edge Generative AI and Agentic AI solutions for our clients on AWS. This role involves hands-on customer engagement, transforming our robust platform capabilities into practical solutions that are deployed, troubleshot, and operated smoothly. You will be instrumental in guiding implementations from initial technical discovery through to successful production go-live and hypercare.
This position offers a dynamic blend of engineering, integration, and direct customer interaction, with approximately 70% dedicated to hands-on engineering and integration, 20% to customer engagement, and 10% to architectural contributions.
Engage directly with customer technical teams to deeply understand application, infrastructure, data, integration, security, and operational needs. Translate these requirements into actionable, implementable solutions.
Participate actively in technical discovery sessions, solution workshops, and deliver compelling demonstrations, proof-of-concepts, and pilot projects. Lead deployment planning and execution for smooth go-live activities.
Implement bespoke Agentic AI solutions leveraging Amazon Bedrock, Amazon Bedrock AgentCore, Python, and leading agent frameworks like LangGraph or LangChain. Configure and customize reusable agents, skills, RAG components, and enterprise connectors tailored to customer environments.
Develop custom integrations using REST APIs, AWS SDKs, and essential enterprise systems when standard connectors are not available. Configure robust security measures including endpoints, authentication, authorization, IAM roles, and API credentials.
Deploy and manage customer solutions on AWS using key services such as Bedrock AgentCore Runtime, Lambda, ECS, and API Gateway. Configure sophisticated RAG and knowledge integrations, ensuring secure access and validation of data.
Implement comprehensive monitoring and logging solutions using Amazon CloudWatch and AWS X-Ray. Execute thorough testing across functional, integration, security, and performance aspects prior to production rollout.
Proactively troubleshoot production issues across the AI stack and AWS infrastructure, driving them to resolution. Analyze logs, traces, and evaluation results to implement corrective actions and optimize solutions for reliability, cost, and performance.
Support CI/CD pipelines, environment promotions, and production deployment activities. Document architecture, configurations, operational procedures, and support guidelines. Conduct knowledge transfer sessions and provide hypercare support. Provide valuable feedback to platform engineering teams for continuous improvement.
A strong foundation in Python programming and software engineering is essential. You should possess hands-on experience with Large Language Models (LLMs), Retrieval Augmented Generation (RAG), prompt engineering, agentic workflows, and multi-agent systems.
Demonstrated experience with Amazon Bedrock and/or Amazon Bedrock AgentCore for production-ready agent solutions is required. Proficiency in REST API development, integration, JSON, YAML, and AWS SDKs is crucial.
Working knowledge of AWS IAM, role-based access control, OAuth, Secrets Manager, authentication, and authorization is necessary for secure integrations. Practical experience with AWS services like ECS, EKS, or Lambda for production deployments is a must.
Familiarity with Git, CI/CD practices, Docker, and production deployment workflows is expected. Experience with logging, monitoring, tracing, debugging, and resolving production incidents is vital.
A good understanding of databases, SQL, enterprise data sources, and RAG implementation patterns is beneficial. Familiarity with Responsible AI principles, security best practices, and enterprise deployment considerations is also important.
Excellent communication skills are required to effectively collaborate with customer technical stakeholders. 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 specifically in Generative AI/Agentic AI), is necessary. Proven experience delivering AI, automation, or cloud solutions into production is a key requirement.
HCLTech
IT Consulting