Role Overview:
As a Vice President AI Engineering & Prompt Architecture Lead in Predictive Science, you will take a lead role in acquiring, managing, and retaining meaningful relationships to deliver outstanding customer experiences. Your focus will be on offering options and finding solutions to help customers with their issues. You will own the technical vision and delivery for a team of prompt engineers and AI/ML model developers building intelligent document processing and data extraction solutions in the KYC/AML domain.
Key Responsibilities:
• Lead and develop a team of 815 prompt engineers and AI/ML developers, set technical direction, run architecture reviews, and define quality standards for prompts and model artifacts.• Architect agentic, multi-step AI workflows chaining classification, extraction, cross-validation, and exception routing with human-in-the-loop checkpoints.• Debug and remediate complex prompt failures such as context-window overflow, instruction drift in long chains, RAG retrieval poisoning, and output/format instability.• Design prompt/model evaluation frameworks measuring accuracy, consistency, robustness, latency, cost-per-call, and hallucination rate.• Operationalize prompt lifecycle management as production code by implementing versioning, CI/CD prompt tests, A/B experiments, rollback, and audited change history.• Guide model selection and optimization balancing accuracy, latency, cost, and data sensitivity.• Design RAG architectures for financial documents including chunking, embeddings, vector store design, re-ranking, and context injection.• Oversee fine-tuning/training workflows, dataset curation, annotation quality, training configurations, and generalization across document variants.• Build and maintain evaluation infrastructure including benchmark/golden datasets, regression suites, and automated scoring to catch regressions pre-production.• Define confidence calibration and escalation logic to estimate uncertainty and route low-confidence outputs to human reviewers with the right context.• Partner with governance/model risk and data engineering to produce validator-ready documentation and ensure robust, refreshed data/annotation/eval pipelines.Qualifications Required:
• 10+ years in NLP/AI/ML or computational linguistics, including 3+ years leading technical teams with direct reports.• Hands-on LLM internals expertise such as tokenization impacts, attention limits, context window management, and temperature/sampling trade-offs.• Proven prompt architecture design/debugging skills including multi-turn chains, few-/many-shot, chain-of-thought, self-consistency, and constitutional AI.• Strong RAG system design experience with embeddings trade-offs, chunking for semi-structured docs, hybrid retrieval, and re-ranking.• Fine-tuning experience with LoRA/QLoRA, instruction tuning, RLHF/DPO, dataset curation, and evaluating tuned vs prompted performance.• Proficiency in Python + ML engineering, PyTorch, Hugging Face, LangChain/LlamaIndex, vector DBs, and API development.• Experience in AI evaluation systems beyond F1, deep understanding of LLM failure modes, and structured output enforcement in production.• Build-vs-buy/model selection track record, leadership under ambiguity, and communication skills with compliance, risk, and business stakeholders.(Note: Preferred qualifications, capabilities, skills, and additional details about the company have been omitted from the Job Description) Role Overview:
As a Vice President AI Engineering & Prompt Architecture Lead in Predictive Science, you will take a lead role in acquiring, managing, and retaining meaningful relationships to deliver outstanding customer experiences. Your focus will be on offering options and finding solutions to help customers with their issues. You will own the technical vision and delivery for a team of prompt engineers and AI/ML model developers building intelligent document processing and data extraction solutions in the KYC/AML domain.
Key Responsibilities:
• Lead and develop a team of 815 prompt engineers and AI/ML developers, set technical direction, run architecture reviews, and define quality standards for prompts and model artifacts.• Architect agentic, multi-step AI workflows chaining classification, extraction, cross-validation, and exception routing with human-in-the-loop checkpoints.• Debug and remediate complex prompt failures such as context-window overflow, instruction drift in long chains, RAG retrieval poisoning, and output/format instability.• Design prompt/model evaluation frameworks measuring accuracy, consistency, robustness, latency, cost-per-call, and hallucination rate.• Operationalize prompt lifecycle management as production code by implementing versioning, CI/CD prompt tests, A/B experiments, rollback, and audited change history.• Guide model selection and optimization balancing accuracy, latency, cost, and data sensitivity.• Design RAG architectures