AI Engineer

Datamatics is seeking a highly motivated AI Engineer with a strong focus on designing, developing, and deploying production-grade LLM-powered applications . The ideal candidate will have hands-on experience with modern GenAI frameworks such as LangChain and LangGraph, and a deep understanding of Retrieval-Augmented Generation (RAG) architectures.

• Design, develop, and deploy scalable AI applications using Python and modern GenAI frameworks (e.g., LangChain, LangGraph, LlamaIndex)
• Build production-ready LLM applications for real-world use cases across public health and enterprise domains
• Integrate state-of-the-art generative AI models to enhance product capabilities and consulting offerings

• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines using advanced techniques such as:
  • Semantic search
  • Hybrid search
  • Re-ranking strategies
• Apply NLP concepts including embeddings, Named Entity Recognition (NER), and text processing to improve model performance
• Fine-tune retrieval and generation strategies for accuracy, latency, and scalability

• Collaborate with Data Engineers and Data Scientists to design scalable, high-performance AI solutions
• Ensure smooth productionization of AI models in collaboration with MLOps teams
• Deploy and manage AI services using Kubernetes and containerization technologies
• Work with cloud platforms (AWS, Azure, or GCP) and big data ecosystems

• Stay updated with the latest advancements in AI, LLMs, and NLP
• Contribute to innovation by experimenting with emerging tools, frameworks, and methodologies
• Drive adoption of best practices in AI engineering and system design

• Bachelor’s or Master’s degree in Computer Science, Engineering, Data Science, or a related field (with focus on AI/ML/NLP)
• 1–3 years of hands-on experience in AI/ML application development
• Strong programming skills in Python

• Experience with GenAI frameworks such as LangChain, LangGraph, and/or LlamaIndex
• Strong understanding of:
  • LLMs and prompt engineering
  • RAG architectures
  • Embeddings and vector databases
• Familiarity with NLP techniques such as NER, semantic search, and text processing
• Experience with:
  • Kubernetes and containerization (Docker)
  • Cloud platforms (AWS, Azure, or GCP)
  • Big data tools (e.g., Apache Spark) and data lake architectures
• Strong problem-solving, analytical thinking, and communication skills

• Experience building production-grade AI/LLM applications
• Exposure to MLOps practices and model lifecycle management
• Familiarity with vector databases (e.g., Pinecone, FAISS, Weaviate)
• Understanding of scalable system design and microservices architecture