As a Senior AI Engineer, you will play a pivotal role in designing and implementing cutting-edge AI solutions that leverage large language models (LLMs) to transform how we process and understand complex data. Your expertise will drive the development of intelligent systems that enhance document understanding, automate information retrieval, and provide actionable insights. This position is crucial for advancing our AI capabilities and delivering innovative solutions that meet the evolving needs of our clients.
Roles and Responsibilities:
Design and implement AI solutions using LLMs for tasks such as summarization, question answering, and document understanding.
Build and optimize retrieval-augmented generation (RAG) pipelines by combining OCR and LLMs for unstructured document processing.
Integrate LLMs and OCR tools, such as Azure Document Intelligence and Tesseract, into scalable applications.
Preprocess scanned and digital documents using OCR to extract structured and semi-structured text for LLM input.
Perform prompt engineering and fine-tuning of LLMs to enhance accuracy and task-specific performance.
Evaluate and monitor LLM+OCR system outputs for quality, bias, and hallucination risks.
Collaborate with cross-functional teams to deliver AI solutions tailored to domain-specific needs.
Stay updated on the latest developments in foundation models, Agentic AI, and OCR technologies.
Qualifications:
Bachelor's or Master's degree in Computer Science, Engineering, or a related field.
4+ years of experience in AI/ML, with a focus on LLMs and prompt engineering.
Proven ability to work independently, demonstrating initiative, ownership, and accountability across all phases of solution development.
Practical understanding of SAFe Agile methodologies, with experience delivering AI/ML solutions in cross-functional Agile teams.
Tools and Technologies:
Hands-on experience with LLM frameworks such as LangChain and Semantic Kernel.
Strong understanding of vector search, embedding models, and semantic retrieval (e.g., FAISS, Pinecone, Azure Cognitive Search).
Proficiency in Python, with experience integrating APIs, function calling, regular expressions, and handling LLM outputs.
Deep expertise in prompt engineering, including few-shot prompting, prompt tuning, prompt chaining, and optimization techniques for task-specific accuracy and cost control.
Solid knowledge of RAG architectures and agent design patterns (e.g., tool use, memory, planning).
Experience with OCR technologies (e.g., Tesseract, Azure Document Intelligence) for document understanding and information extraction from scanned or image-based content.
Familiarity with LLM platforms and tools like Azure OpenAI, LLMOps.
Experience deploying LLM-based applications in cloud environments, with attention to performance, reliability, and scalability.