Job Description
<h3>π Description</h3> β’ Help build the next-generation AI agents.
β’ Design, implement, and optimize retrieval-augmented generation pipelines.
β’ Develop and maintain recommendation engines leveraging LLMs and MCPs.
β’ Train, optimize, and deploy state-of-the-art language models for conversational and semantic tasks.
β’ Monitor model drift, bias, and accuracy; implement feedback loops for continuous improvement.
β’ Architect and manage scalable data warehouses to support high-volume transactional and behavioral data.
β’ Collaborate closely with product managers, software engineers, and UX designers.
β’ Present complex technical concepts and model insights to various stakeholders.
β’ Mentor junior engineers and foster a culture of knowledge-sharing and best practices. <h3>π― Requirements</h3> β’ Bachelorβs or Masterβs degree in Computer Science, Engineering, Data Science, or a related field.
β’ 5+ years of experience in machine learning and NLP, including hands-on work with LLMs and prompting techniques.
β’ Proven track record building RAG systems and recommendation engines in production environments.
β’ Expertise in Python, SQL, and version control (Git); familiarity with ML frameworks (PyTorch, TensorFlow) and LangChain-like libraries.
β’ Strong problem-solving skills, attention to detail, and a bias for action.
β’ Excellent verbal and written communication skills, with the ability to distill complex ideas for diverse audiences.
β’ Experience with Django or other web frameworks is a plus.