Job
Description
Position Overview We are hiring five AI Engineers with 12 years of experience to join our dynamic team in Hyderabad. The ideal candidates will have a solid foundation in Large Language Models (LLMs) , LangChain , and Generative AI (GenAI) frameworks. This is a great opportunity to work on innovative AI solutions, contributing to projects that integrate LLMs , prompt engineering , RAG pipelines , and cloud-based deployments . Key Responsibilities Contribute to the design and development of AI-powered applications utilizing LLMs (GPT-3.5, GPT-4, Gemini). Assist in building LangChain-based pipelines and workflows, including LangSmith and LangGraph . Support the implementation of Retrieval-Augmented Generation (RAG) frameworks using vector databases such as ChromaDB . Apply prompt engineering techniques to optimize model responses and improve contextual accuracy. Develop RESTful APIs using Flask or FastAPI to enable model consumption in production environments. Write and manage data workflows using SQL , PySpark , and Spark SQL . Deploy and monitor models on Azure Machine Learning or AWS Bedrock platforms. Collaborate with cross-functional teams, including data scientists, engineers, and business stakeholders. Required Skills Proficiency in Python , SQL , PySpark , and Spark SQL Hands-on experience with LLMs : GPT-3.5, GPT-4, Gemini Knowledge of LangChain , LangSmith , LangGraph Familiarity with Vector Databases (e.g., ChromaDB) and embeddings Experience with prompt engineering and RAG-based architectures Exposure to cloud platforms such as Azure ML or AWS Bedrock Strong understanding of REST APIs and version control systems (Git/GitHub) Preferred Qualifications Bachelor's degree in Computer Science, Artificial Intelligence, Data Science, or a related field Internship or academic project experience in NLP, LLMs, or GenAI technologies Familiarity with MLOps tools and practices (e.g., CI/CD, Airflow) Strong problem-solving abilities, attention to detail, and a collaborative mindset
