Track Lead (Support & Operations) (IN)
HCLTech
HCLTech
Join our team as a Forward Deployment Engineer (FDE) and play a key role in architecting, customizing, integrating, and deploying cutting-edge Generative AI and Agentic AI solutions on AWS for our enterprise clients. This hands-on, customer-facing role is crucial for transforming reusable platform capabilities into robust, production-ready customer solutions. You will own the entire implementation lifecycle, from initial technical discovery through production go-live and post-launch hypercare.
Your responsibilities will span approximately 70% engineering and integration work, 20% direct customer interaction, and 10% contributions to architecture. This position requires a strong blend of technical expertise, problem-solving acumen, and customer engagement skills.
Engage directly with customer technical teams to thoroughly understand their application, infrastructure, data, integration, security, and operational needs, translating these into actionable implementation plans.
Actively participate in technical discovery sessions, solution workshops, demonstrations, proof-of-concepts, pilots, deployment planning, and go-live activities.
Implement bespoke Agentic AI solutions utilizing Amazon Bedrock, Amazon Bedrock AgentCore, Python, and leading agent frameworks like LangGraph, LangChain, or Strands Agents.
Configure and tailor reusable agents, skills, workflows, RAG components, prompts, and enterprise connectors for specific customer environments.
Develop custom integrations leveraging REST APIs, AWS SDKs, MCP tools, databases, ITSM platforms, monitoring systems, identity services, and proprietary applications where standard connectors are not available.
Secure customer environments by configuring endpoints, authentication, authorization, IAM roles/policies, OAuth/API credentials, and Secrets Manager.
Deploy and manage customer solutions on AWS using a variety of services including Amazon Bedrock AgentCore Runtime, Lambda, ECS, EKS, API Gateway, EventBridge, Step Functions, SQS/SNS, and S3.
Configure RAG and knowledge integrations, including data ingestion, retrieval, and access control, using customer-approved search, vector, database, and storage services.
Implement comprehensive logging, tracing, metrics, monitoring, evaluation, and operational dashboards using Amazon Bedrock AgentCore Observability, CloudWatch, and AWS X-Ray/OpenTelemetry.
Conduct thorough functional, integration, security, performance, and user acceptance testing prior to production rollout.
Troubleshoot and resolve production issues across agents, models, prompts, tools, APIs, RAG, authentication, networking, and AWS infrastructure, driving them to closure.
Analyze logs, traces, metrics, and latency data to identify patterns and implement corrective actions for optimization.
Support CI/CD pipelines, environment promotion, versioning, releases, rollbacks, and production deployment activities.
Optimize solutions for reliability, scalability, low latency, usability, and cost-effective AI inference.
Document customer architecture, integrations, configuration, deployment procedures, operational runbooks, and troubleshooting guides.
Facilitate knowledge transfer sessions to customer teams and internal support staff, and provide support during production hypercare phases.
Provide structured feedback to Agent Development and Platform Engineering teams on recurring customer requirements to drive platform improvements.
Possess strong Python programming skills and fundamental software engineering principles.
Demonstrate hands-on experience with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), prompt engineering, agentic workflows, tool/function calling, structured outputs, and multi-agent systems.
Showcase practical experience with Amazon Bedrock and/or Amazon Bedrock AgentCore for production agent solutions.
Exhibit strong REST API development and integration capabilities, with proficiency in JSON, YAML, AWS SDKs, and enterprise APIs.
Have a working knowledge of AWS IAM, role-based access, OAuth, API keys, Secrets Manager, authentication, authorization, and secure service-to-service integration.
Provide hands-on experience with AWS and at least one production deployment model using ECS, EKS, Lambda, or AgentCore Runtime.
Be experienced with Git, CI/CD, Docker, and established production deployment practices.
Possess experience in logging, monitoring, tracing, debugging, and troubleshooting production incidents.
Have a good understanding of databases, SQL, enterprise data sources, and RAG implementation patterns.
Understand Responsible AI principles, security best practices, data protection, and enterprise deployment requirements.
Communicate effectively and comfortably interact with customer technical stakeholders.
Preferred qualifications include experience with Amazon Bedrock AgentCore components, MCP, A2A, Terraform/Infrastructure-as-Code, various AWS services (Lambda, ECS, EKS, API Gateway, etc.), ITSM platforms like ServiceNow, and supporting customer POCs and production rollouts.
Candidates should hold a Bachelor's or Master's degree in Computer Science, Engineering, Information Technology, or a related field, with 4-7 years of overall software or cloud engineering experience, including at least 2 years specifically in Generative AI/Agentic AI. Proven experience delivering an AI, automation, or cloud solution into production is essential. We seek customer-oriented individuals with strong ownership, execution bias, and excellent problem-solving abilities, comfortable working across AI engineering, AWS cloud, integration, and operations.
HCLTech
IT Consulting