Track Manager (Support & Operations) (IN)
HCLTech
HCLTech
Join us as a Forward Deployment Engineer (FDE) to design, build, and deploy cutting-edge enterprise Generative AI and Agentic AI solutions powered by Anthropic Claude.
You will collaborate directly with customers, understanding their unique environments and requirements to translate them into robust AI solutions. This role involves integrating agents with existing enterprise applications, configuring critical security and governance controls, and guiding solutions from initial development through validation, production deployment, and post-launch support.
Success in this position requires a strong foundation in software engineering and API development, coupled with practical experience in Large Language Models (LLMs), agentic AI, enterprise integrations, AI security, evaluation, and production operations.
Key responsibilities include:
- Engaging with customers to deeply understand business, technical, security, data, and operational needs. - Conducting technical discovery, workshops, and demonstrations, and leading proof-of-concepts and pilot implementations. - Translating complex customer requirements into practical Generative AI and Agentic AI solutions. - Collaborating with customer architects, application teams, and security personnel to ensure successful deployments. - Owning customer technical workstreams from implementation to post-go-live hypercare. - Designing, developing, and deploying enterprise AI agents using Anthropic Claude, customizing instructions, prompts, tools, and workflows. - Building multi-agent and tool-driven workflows tailored to specific customer use cases. - Developing custom logic and orchestration using Python and other relevant languages. - Implementing robust features such as tool calling, structured outputs, context management, and error handling for production-ready AI applications. - Integrating AI agents with enterprise applications via REST APIs, SDKs, webhooks, and other mechanisms. - Building custom integrations where standard connectors are unavailable. - Configuring security controls, including authentication, authorization, and access management. - Mapping customer-specific data models, business rules, and workflows. - Integrating enterprise knowledge sources and customer data using RAG and retrieval solutions. - Implementing enterprise security requirements for AI applications, including access controls and data protection. - Supporting customer needs for data retention, privacy, and compliance. - Developing and implementing evaluation frameworks for AI components and end-to-end workflows. - Monitoring AI agent quality, performance, and cost. - Deploying customer AI applications and supporting services into approved environments. - Integrating AI services with customer infrastructure, including containerized and serverless platforms. - Implementing CI/CD pipelines, configuration management, and release processes. - Performing comprehensive testing, including functional, integration, security, and performance testing.
To excel in this role, you should possess:
- Hands-on experience with the Anthropic Claude API and platform for production Generative AI and Agentic AI solutions. - Experience with Claude tool use, structured outputs, prompt engineering, context management, and agentic workflows. - Proficiency in Python, with strong software engineering practices including Git, testing, and debugging. - A solid understanding of LLMs, Generative AI, RAG, prompt engineering, agentic AI, tool calling, and multi-agent workflows. - Extensive experience developing and consuming REST APIs and implementing enterprise integrations. - Deep understanding of authentication and authorization mechanisms, such as OAuth, API keys, RBAC, and secrets management. - Experience deploying production AI applications using technologies like Docker, Kubernetes, or serverless platforms. - Familiarity with CI/CD pipelines and production software deployment practices. - Experience with AI observability, evaluation, logging, tracing, and production troubleshooting. - Knowledge of enterprise data sources, databases, APIs, search, and RAG implementation. - Understanding of Responsible AI principles, AI security, privacy, compliance, and enterprise governance. - Strong communication skills and the ability to engage directly with enterprise customers. - The capacity to independently manage customer requirements from initial discovery through to production deployment. - A Bachelor’s or Master’s degree in Computer Science, Engineering, Information Technology, or a related field. - 4–7 years of overall software engineering, cloud, or AI engineering experience, with a minimum of 2 years focused on Generative AI / Agentic AI. - Demonstrated success in delivering at least one AI solution into a production environment. - Proven experience working with enterprise customers or customer-facing engineering teams.
We are seeking individuals with a strong customer-facing presence, excellent programming and debugging capabilities, and comfort working across AI, APIs, enterprise applications, data, security, and operations. A strong sense of ownership, execution bias, problem-solving skills, and the ability to navigate ambiguous and rapidly changing AI environments are essential.
HCLTech
IT Consulting