Vice President - Data Scientist : Fraud Modeling (Pune)

AIM Fraud analytics team is seeking an experienced and innovative Data Scientist to join our Fraud Modeling / Gen AI team to transform fraud detection and prevention. As a subject matter expert in data science, you will be responsible for the development and deployment of cutting-edge data science solutions that enhance fraud detection and reduce false positives and optimize operational efficiency.

Key Responsibilities:

• Lead the design and implementation of generative AI use cases, from ideation to production.

• Build and tune LLM-based applications using platforms like Vertex, GPT, Hugging Face, etc.

• Create robust prompt engineering strategies and reusable prompt templates.

• Integrate generative AI with enterprise applications using APIs, knowledge graphs, vector databases (e.g., PG Vector, Pinecone, FAISS, Chroma), and orchestration tools.

• Collaborate with Tech and business teams to identify opportunities and build solutions.

• Responsible for model development, validation and testing of fraud detection models, including statistical analysis, data validation and model performance evaluation.

• Ensure compliance with regulatory requirements and industry best practices in fraud detection and model validation.

• Responsible for documenting the model development documents for MRM approvals and governance purposes.

• Stay current on GenAI trends, frameworks (LangChain, LlamaIndex), and research.

• Mentor junior team members and promote a culture of experimentation and learning.

• Stay abreast of advancements in Gen AI, LLMs, and fraud prevention technologies, applying relevant innovations to projects.

• Specialization in fraud or risk domain preferred

Qualifications:

• 11+ years of hands-on experience in data science, or AI/ML roles.

• 7+ years’ experience in statistical analysis with working knowledge of at least one of the following statistical software packages: Python (Must), Hive, Spark, SAS Strong quantitative, analytical, and problem-solving skills; knowledge of probability theory, statistics, mathematical finance, econometrics, numerical methods

• 2+ years of hands-on experience specifically with generative AI or LLMs.

• Strong understanding of statistical concepts and modelling techniques including traditional and advanced ML algorithms

• Strong programming skills in Python, and familiarity with libraries like Transformers, LangChain, LlamaIndex, PyTorch, or TensorFlow.

• Working knowledge of retrieval-augmented generation (RAG) pipelines and vector databases.

• Understanding of MLOps / LLM Ops, model evaluation, prompt tuning, and deployment pipelines

• Experience building applications with OpenAI, Anthropic Claude, Google Gemini, or open-source LLMs.

• Familiarity with regulatory requirements and guidelines related to risk model validation

• Strong communication skills and the ability to partner with both technical and non-technical stakeholders.