AI Engineer

Overview

We are looking for a talented and driven AI Engineer to lead the development of our next-generation Smart Audit platform. In this role, you will design, build, and deploy machine learning models and Large Language Model (LLM) applications designed to automate complex audit processes. You will transform how we analyze financial records, contracts, and operational data—turning manual, error-prone sampling into automated, 100% population risk scanning.

Key Responsibilities

Model Development: Design and deploy AI/ML models specifically for anomaly detection, fraud identification, and automated compliance checking.

LLM & NLP Pipeline Engineering: Build robust Retrieval-Augmented Generation (RAG) pipelines to extract, summarize, and cross-reference clauses from massive volumes of unstructured legal and financial documents.

Data Pipeline Construction: Collaborate with data engineers to ingest, clean, and structure messy, multi-format audit data (PDFs, Excel sheets, ERP system dumps).

System Integration: Integrate AI modules into existing auditing software and enterprise resource planning (ERP) systems via secure, scalable APIs.

Model Monitoring & Evaluation: Implement rigorous evaluation frameworks to ensure model accuracy, mitigate hallucinations in LLMs, and minimize false positives/negatives.

Security & Explainability: Ensure all AI models adhere to strict data privacy standards (e.g., GDPR, SOC2) and provide explainable outputs so human auditors can easily verify the AI's logic.

Technical Skills & Qualifications

Required:
Education: Bachelor’s or Master’s degree in Computer Science, Data Science, Artificial Intelligence, or a related quantitative field.

Programming: Mastery of Python and standard ML libraries (e.g., PyTorch, TensorFlow, Scikit-Learn, Pandas).

Generative AI Frameworks: Proven experience with LLM orchestration tools like LangChain, LlamaIndex, or AutoGen, and experience fine-tuning or prompting frontier models (OpenAI, Anthropic, open-source models like Llama).

NLP & OCR: Strong background in Named Entity Recognition (NER), text classification, and advanced Document AI/OCR tools (e.g., Azure Document Intelligence, AWS Textract, Unstructured).

Vector Databases: Experience working with vector stores such as Pinecone, Milvus, Qdrant, or PGVector.

Preferred (Nice-to-Have):
Domain knowledge in finance, accounting, forensic auditing, or corporate compliance.

Experience with Graph Neural Networks (GNNs) or Knowledge Graphs for mapping corporate entities and transactions.

Familiarity with cloud platforms (AWS, GCP, or Azure) and MLOps tools (MLflow, Kubeflow, Weights & Biases).

Soft Skills & Culture Fit

Analytical Mindset: A sharp eye for detail; you enjoy finding the "needle in the haystack."

Strong Communicator: Ability to explain complex AI concepts to non-technical stakeholders (like financial auditors and legal counsels).

Problem Solver: Comfortable working with ambiguous, unstructured, and often messy real-world data.