AI/ML Engineer

About the job

Job Title : AI/ML Engineer Experience- 4 to 8 years Location: Vashi, Navi Mumbai (Work from Office) Key Responsibilities • Design and implement RAG pipelines, including support for multimodal inputs such as text, tables, and images. • Build AI applications that process unstructured financial documents (e.g., PDF, Word, scanned files) to extract insights, generate content, and enable Q&A. • Develop solutions that convert financial documents into structured regulatory formats like XBRL/iXBRL. • Integrate LLMs into production systems using FastAPI or similar frameworks. • Use OCR techniques to extract information from scanned documents and embedded images. • Collaborate with data scientists, engineers, and product managers to deliver business-aligned AI solutions. • Optimize model performance for scalability, accuracy, and cost-efficiency. • Contribute to the architecture and design of AI systems and participate in technical decision-making. • Keep up to date with advancements in AI/ML, especially in the areas of RAG, multimodal processing, and LLMs. Mandatory Skills and Qualifications • 5+ years of experience in AI/ML engineering or related roles. • Hands-on experience with RAG pipelines, including chunking, embeddings, vector databases, and query response optimization. • Experience working with unstructured data (PDFs, scanned documents, images) and converting them into structured information. • Strong knowledge of OCR techniques and tools for processing scanned documents. • Proficiency in developing APIs using FastAPI (or similar frameworks) for AI model integration. • Experience deploying AI solutions in containerized environments (Docker and Kubernetes). • Familiarity with financial documents such as annual reports, and ability to work with domain-specific concepts like revenue, balance sheets, etc. • Experience with at least one vector database (Qdrant preferred, others acceptable). • Understanding of multimodal AI techniques and experience working with both text and image-based inputs. • Strong communication and problem-solving skills, with the ability to work in cross-functional teams. Preferred Skills (Good to Have) • Experience with LLM fine-tuning techniques such as SFT, PEFT, or LoRA. • Knowledge of model development using PyTorch or TensorFlow. • Familiarity with LangChain, LlamaIndex, CrewAI, AutoGen, or similar LLM orchestration frameworks. • Exposure to Azure OpenAI, OpenAI APIs, or similar cloud-based LLM providers. • Experience with MLOps practices, including model lifecycle management and monitoring. • Prior work on time series forecasting or classical ML models (e.g., using Scikit-learn). • Familiarity with Azure Document Intelligence or similar document AI platforms. • Experience working on multilingual or translation-based LLM systems. • Contributions to open-source AI/ML projects or relevant published research.

Requirements

• RAG Pipelines
• OCR Techniques
• FastAPI
• Containerized Environments
• Multimodal Processing

Qualifications

• Bachelor’s or master’s degree in: Computer Science / Engineering, Mathematics, Statistics or related quantitative fields

Preferred Technologies

• RAG Pipelines
• OCR Techniques
• FastAPI
• Containerized Environments
• Multimodal Processing