AI/ML Engineer

About the Project:
We’re looking for a skilled AI/ML Engineer to lead the development of intelligent components for a conversational chatbot and advanced search system. This includes everything from building solid data pipelines to integrating LLMs and optimizing semantic search.

🔧 What You’ll Be Working On:

• Review and analyze existing data sources and schemas.
• Design and implement ETL pipelines for both structured and unstructured data.
• Generate embeddings and manage vector databases (PGVector/PostgreSQL).
• Build and optimize similarity search and ranking algorithms.
• Fine-tune LLM prompts for chatbot interactions and contextual replies.
• Develop logic for user intent detection and dynamic response generation.
• Collaborate with the engineering team on deployment, APIs, and testing.
• Implement feedback loops to continuously improve model performance.
• Ensure role-based access, metadata tracking, and performance tuning.
• Deliver scalable, production-ready AI/ML components.

✅ We’re Looking For Someone Who Has:

• 5+ years of hands-on experience in AI/ML engineering, ideally in production environments.
• Strong Python skills: Pandas, NumPy, FastAPI, Langchain, etc.
• Practical experience working with LLMs (OpenAI, AWS Bedrock) and prompt engineering.
• Deep knowledge of embeddings, semantic search, and NLP techniques.
• Solid background with ETL workflows from diverse sources (APIs, SQL, documents, images).
• Experience working with vector databases — PGVector is a strong plus.
• Familiarity with unstructured data handling and metadata management.
• Hands-on deployment experience in Dockerized environments.
• Understanding of role-based access control and personalization logic.
• Strong communication and team collaboration skills, with the ability to lead technical decisions.
   

💬 If you're excited about building LLM-powered systems and solving real-world search + chatbot challenges — we’d love to talk.