Gen AI Engineer

Role & responsibilities

The GenAI Engineer will be responsible for designing, developing, and deploying AI-driven systems focused on document parsing, context understanding, and knowledge graph construction. The role combines expertise in generative AI models, large language model (LLM) frameworks, and graph-based data representation. The engineer will build scalable document understanding pipelines, extract relationships from unstructured data, and construct knowledge graphs (using technologies such as Neo4j) to enable intelligent information retrieval and reasoning across enterprise datasets.

• Design and develop AI pipelines for document parsing, information extraction, and text understanding using LLMs and NLP techniques.
• Develop and refine algorithms for knowledge graph construction, entity linking, and relationship extraction from text corpora.
• Implement GenAI systems for summarization, semantic search, and contextual reasoning using retrieval-augmented generation (RAG).
• Work with vector databases, embedding generation, and model fine-tuning for domain-specific applications.
• Build and maintain scalable APIs and backend services to integrate GenAI capabilities with enterprise applications.
• Design and optimize Neo4j-based knowledge graphs to represent and query structured relationships from unstructured data.
• Collaborate with data scientists, AI/ML engineers, and software teams (frontend/backend) to integrate GenAI features into production.
• Evaluate and apply frameworks such as LangChain, LlamaIndex, Hugging Face, and OpenAI APIs for document intelligence workflows.
• Develop algorithms for semantic search, reasoning, and document-to-graph alignment using graph embeddings and transformer architectures.
• Ensure data quality, governance, and compliance with enterprise security and information management standards.
• Document research findings, maintain technical design specifications, and support continuous model improvement.

Preferred candidate profile

• Bachelors or Masters degree in Computer Science, Artificial Intelligence, Data Science, or related field.
• 8–10 years of experience in AI, NLP, or Machine Learning with hands-on GenAI or document understanding experience.
• Strong proficiency in Python and familiarity with AI frameworks (PyTorch, TensorFlow).
• Experience with LLM-based document processing, prompt engineering, fine-tuning, and RAG pipelines.
• Hands-on experience with graph databases such as Neo4j and query languages like Cypher.
• Strong understanding of NLP, entity recognition, text classification, and relationship extraction.
• Experience with LangChain, LlamaIndex, Hugging Face Transformers, and OpenAI APIs.
• Knowledge of embeddings, vector stores, and semantic search algorithms.
• Familiarity with cloud platforms (AWS, Azure, GCP) for training and deploying AI models.
• Strong software engineering skills — version control, modular design, testing, and documentation.
• Excellent problem-solving abilities and cross-team collaboration skills.
• Exposure to regulatory and quality systems in medical device software development (e.g., ISO 13485, IEC 62304).

Preferred / Secondary Skills

• Experience with ontology design or knowledge representation learning.
• Exposure to enterprise search systems such as ElasticSearch, FAISS, Pinecone.
• Understanding of multimodal AI (text, image, audio).
• Experience with MLOps techniques for deployment and monitoring.
• Background in biomedical or healthcare text analytics is a plus.