Senior Manager

Job Description Role description A Position Overview Position Title Prompt Engineer, GenAI Specialist Department TDA-BSG (IT) Level/ Band SM/AVP Role Summary: The Prompt Engineer, GenAI Specialist will be responsible for designing, developing, and optimizing prompt engineering strategies and GenAI solutions. The ideal candidate should have hands-on experience with LLMs, agentic AI frameworks, and RAG architectures, and must have successfully deployed at least one GenAI solution in a production environment. B Organizational Relationships Reports to AVP/VP Supervises NA C Job Dimensions Geographic Area Covered PAN India Stakeholders Internal TDA-BSG and all other TATA AIA internal departments External Partners D Key Result Areas Design & Optimize Prompts Design and refine prompts for LLMs to optimize performance across applications. Craft high-quality prompts for a variety of modestextual quizzes, policy Q&A, recommendation generation, and voice interactionsensuring accuracy, clarity, and engagement. Continuously iterate based on performance metrics and user feedback. Implement Advanced Techniques Apply techniques such as few-shot prompting, chain-of-thought reasoning, RAG-contextual prompts, and reflection, to enhance the bot's comprehension and decision-making. Develop and deploy agentic AI solutions using LangChain, Hugging Face, OpenAI, etc. Build and maintain RAG-based architectures for conversational AI and chatbots. Implement GenAI models and algorithms in production environments. - Responsible & Inclusive Prompting Ensure prompts are culturally sensitive, inclusive, and ethically sound. Embed guardrail designs and help prevent prompt injection vulnerabilities. Integrate agents with external APIs, vector stores, and structured data sources. Fine-tune LLMs and apply quantization, scaling, and pruning techniques. - Collaborate Across Teams Work closely with product management, data scientists, engineers, and UX designers to gather insurance domain requirements and shape prompt design strategy. Collaborate with cross-functional teams to deliver scalable AI solutions Evaluate & Report Performance Monitor prompt effectiveness using defined KPIsfor example, user engagement in quizzes, recommendation accuracy, cost per API call, and customer satisfaction. Report insights and refine prompts iteratively. - Build & Maintain Prompt Libraries Develop reusable prompt templates and documentation to scale across use cases. Promote best practices and knowledge sharing. Stay Updated Keep abreast of the latest NLP, LLM, and prompt engineering research and tools, and integrate new learnings into your work. Ensure multi-cloud deployment compatibility and workflow automation. E Competencies (Please copy paste from Competency Dictionary) Competency For Proficiency Scale Proficiency Scale Description Timely Decision Making 5 Uses experience and industry awareness while taking decisions to help improve effectiveness and output. Displays strong analytical skills to identify emerging trends and patterns and anticipates potential problems / issues. Solves problems even in ambiguous or risk situations by selecting a course of action based on logical assumptions and factual information, taking into consideration resource constraints and organizational values to solve problems, in line with the set regulations and guidelines. Encourages others to take calculated decisions after evaluating the pros and cons. Functional Excellence 4 Displays a clear understanding of the processes, regulatory framework & market awareness pertaining to own and related markets and helps the team to gain knowledge. Uses business/market awareness and information made available by various processes to enhance overall effectiveness of the function/department and to re-engineer processes. Identify potential hurdles and sets appropriate milestones, systems and processes for others to follow and monitors their progress against the set milestones. Drive for Results 5 Guides organizational initiatives ensuring effective planning and resource utilization. Inspires team to proactively deliver results even in new situations without losing focus on process discipline. Creates a high-performance work climate for individuals and teams to deliver by synergizing multiple systems and departments Customer Focus and Consumer Focus 4 Analyzes the market trends, anticipates customer needs and adopts the best solutions that will exceed the customer expectations while meeting organizational SOP's. Stretches self and team to deliver customer delight. Building and Managing Relationships 5 Establishes long term partnerships with all the parties who can play a pivotal role in guarding the business interest of the organization with a focus on developing mutually beneficial relationships. Presents information persuasively, with skill and power, seeking to influence an audience of critical importance. Is able to deliver difficult or ambiguous messages with clarity, tact and diplomacy. Is able to convey the right message to the right person in the right context. Taking Ownership 5 Leads by example and puts in place strategies and processes to foster a culture of accountability for focused working, to ensure achievement of the tasks within the quality, time and budgetary parameters within the team. G Skills Required Technical: Skill Table Experience in Years Self-rating on scale of 5 Prompt Engineering 3+ 4 LLMs (e.g., OpenAI GPT, Llama, Google Gemini, Anthropic Claude, TensorFlow) 4+ 4 Agentic AI 2+ 4 Retrieval-Augmented Generation (RAG) architectures 2+ 4 Conversational AI & chatbot development 5+ 4 Python 7+ 4 ML/AI 7+ 4 Behavioral Essential Desired Interpersonal skills Communication skills Creative thinking skills Supervising/Leadership skills Teamwork Skills Influencing skills Relationship Building skills Decision making skills H Incumbent Characteristics Essential Desired Qualification Bachelor's or Master's degree in Computer Science, Data Science, AI/ML, Linguistics, or similar. Proficiency in prompt engineering for LLMs (e.g., GPT-series, Hugging Face models) Experience with advanced techniques: chain-of-thought prompting, in-context learning, RAG. Strong analytical skills: ability to define metrics, conduct A/B tests, and refine prompts. Familiarity with AI tooling (e.g., LangChain, OpenAI toolkits) a plus. Expert in Python with strong experience in data analysis, ML/AI, automation, and API development, plus hands-on exposure to GenAI/LLMs and cloud deployment. Certification in GenAI or LLM technologies Experience 8-10 years in Python, ML/AI and conversational AI with 3+ years of experience in GenAI LLMS, Prompt Engineering, RAG & Agentic AI with at least one production deployment Experience with multi-cloud deployments and advanced RAG architectures Prior exposure to insurance, financial services, or claims workflows is highly desirable. Experience building customer-facing AI/content workflows is a bonus.