Associate AI Engineer

Key Responsibilities:

• Assist in the development, testing, and deployment of AI chatbots using local and cloud-based LLMs.
• Support in building RAG (Retrieval-Augmented Generation) systems, including vector search and semantic retrieval.
• Work with Qdrant and embedding models to manage collections, vectors, and similarity search.
• Help develop FastAPI endpoints for AI services and WhatsApp/other messaging integrations.
• Participate in processing training data, embeddings, and conversation history pipelines.
• Implement and refine LLM-based intent detection, response ranking, and fallback systems.
• Collaborate on model optimization, prompt tuning, and improving response accuracy.
• Assist in deploying real-time AI systems for customer service automation.
• Contribute to knowledge base creation, FAQ structuring, and dynamic response generation.
• Write clean, maintainable, and well-documented code for AI modules.
• Stay updated on conversational AI, RAG methodologies, LLM improvements, and vector database innovations.
• Support integrating AI services into cloud environments and multi-tenant architectures.

Required Skills & Qualifications:

• Bachelor’s degree in Computer Science, AI, Data Science, or a related field.
• 0.5 – 2 years of experience working on AI/ML or chatbot projects.
• Hands-on experience with LLMs (OpenAI, Ollama, Hugging Face) and prompt engineering.
• Understanding of vector databases such as Qdrant, Pinecone, or ChromaDB.
• Experience working with embedding models, semantic search, or RAG pipelines.
• Proficiency in Python, especially FastAPI, async workflows, and API development.
• Familiarity with supervised/unsupervised ML concepts and evaluation techniques.
• Understanding of REST APIs, Git, and version control workflows.
• Good analytical, debugging, and problem-solving skills.
• Ability to work in a collaborative, fast-paced engineering environment.
• Exposure to cloud platforms (AWS/GCP/Azure) for deploying AI applications.
• Basic understanding of MLOps, retraining pipelines, or model monitoring.

Job Type: Full-time

Work Location: In person