Job Summary
"OVERVIEW OF THE ROLE The AI Engineer – LLM Platform Support & Prompting Systems is a critical role within HCLTech’s Life Sciences and Healthcare division, focusing on the integration, configuration, and optimization of large language models (LLMs) from major platforms such as Azure OpenAI, Anthropic, OpenAI API, Vertex AI, GPT‑4/5, Claude, Gemini, Mistral, and Llama 3. The role is instrumental in designing intelligent prompting systems and maintaining structured AI configurations to enhance the software development lifecycle, engineering, operations, and documentation processes. The candidate will contribute to the deployment and seamless support of AI-driven solutions, directly impacting the company’s ability to deliver innovative healthcare technology. DETAILED RESPONSIBILITIES - Production support for GenAI applications across development, test, and production environments. - Develop, maintain, and optimize structured system prompts, context hierarchies, and AI workspace configurations across multiple LLM platforms. - Design and implement intelligent prompting mechanisms that improve accuracy, consistency, and domain-specific outcomes in Life Sciences and Healthcare applications. - Deploy, integrate, and troubleshoot AI solutions leveraging cloud platforms (Azure, Google Cloud, etc.) and APIs for LLMs. - Collaborate with cross-functional teams to ensure AI configurations meet engineering, operational, and documentation standards. - Support offshore engineering teams with expertise in cloud deployment, API integration, and issue resolution for LLM-based systems. - Utilize scripting and automation tools (Python, Bash, PowerShell) to streamline workflows, automate deployments, and enhance system reliability. - Monitor AI workspace performance, identify potential improvements, and proactively resolve technical challenges. - Maintain up-to-date documentation and best practices for AI prompt engineering and workspace orchestration. SKILL REQUIREMENTS AWS CloudWatch, Dynatrace Grafana BigPanda GPT-5.4 mini, GPT-5.4, Gemini 2.5 Pro, Claude Sonnet, GPT-4o, gpt-image-1.5, and other Generative AI models API-based services used for application integration and functionality Nobl9 AWS Console GitHub ServiceNow - Proven hands-on experience deploying and supporting multiple LLM platforms (e.g., GPT‑4/5, Claude, Gemini, Mistral, Llama 3). - Strong background in system prompting, context configuration, and AI workspace orchestration. - Expertise in cloud deployment (Azure, Google Cloud, AWS) and API integration. - Proficiency in scripting and automation tools such as Python, Bash, or PowerShell. - Solid understanding of software development lifecycle and best practices in AI implementation. - Excellent analytical, troubleshooting, and problem-solving skills. - Effective communication and collaboration abilities, including experience working with offshore teams. GenAI Application Support Azure OpenAI, OpenAI API Anthropic Claude, Google Gemini, Mistral, Llama Prompt Engineering & Context Management RAG (Retrieval Augmented Generation) Vector Databases & Semantic Search Azure, AWS, Google Cloud Platforms REST API Integration & Troubleshooting Python, PowerShell, Bash Incident, Problem & Change Management (ITIL) OTHER REQUIREMENTS - Experience in Life Sciences and Healthcare AI applications. - Familiarity with regulatory and compliance standards relevant to healthcare technology. - Certifications in cloud computing or AI technologies (e.g., Azure AI Engineer, Google Cloud Professional). - Prior involvement in domain-specific AI prompt engineering projects. Tools/Technologies - AWS CloudWatch, Dynatrace - Grafana - BigPanda - GPT-5.4 mini, GPT-5.4, Gemini 2.5 Pro, Claude Sonnet, GPT-4o, gpt-image-1.5, and other Generative AI
Key Responsibilities
2. To undertake training programs for new joinees
3. To perform knowledge transition during project enhancements
4. To document all the defined processes and the methods of resolving the ticket| troubleshooting| etc.
5. To update self on latest technologies and related areas