We are looking for a highly motivated AI Engineer to join our growing team and contribute to the design, development, and deployment of cutting-edge AI-powered applications. In this role, you will work at the intersection of language models, agentic workflows, and full-stack systems.

You’ll play a key part in shaping how our AI solutions interact with unstructured data, external APIs, and end users. This position is ideal for someone with 3–5 years of hands-on experience building AI/ML systems, particularly those involving LLM-based workflows and vector databases. Your work will directly influence product functionality, user experience, and overall system performance.

Key Responsibilities

• Build and deploy Retrieval-Augmented Generation (RAG) systems using vector databases (e.g., Qdrant, FAISS, Pinecone). 
• Write clean, modular Python code for data pipelines, LLM integration, and API handling.
• Develop tools for LLM output evaluation, testing, and monitoring
• Build interactive Streamlit UIs to showcase real-time LLM applications like document Q&A and external API agents. 
• Integrate external data from public APIs for agent-based decision flows.
• Preprocess, chunk, embed, and index unstructured data (PDFs, text) using embedding models and vector stores.
• Collaborate with full-stack developers to integrate AI modules into production systems.
• Optimize AI systems for performance, latency, and accuracy in real-world deployments.
• Stay current with developments in LLMs, vector search, prompt engineering, and agentic AI frameworks.

Required Qualifications & Skills:

• Bachelor’s or master’s degree in computer engineering, Computer Science, Data Science, or a related field.
• 3–5 years of hands-on experience in AI/ML application development.
• Strong command of Python (including pandas, NumPy, Pytest).
• Experience with Vector database and its implementation.
• Proficient in working with vector databases like Qdrant, FAISS, or Pinecone.
• Good understanding of RAG architecture, prompt engineering, and LLM evaluation techniques.
• Experience with Streamlit or similar frontend tools for data app development.
• Familiarity with document preprocessing, embedding strategies, and indexing.
• Strong knowledge of Git, unit testing, and clean code principles.
• Excellent analytical, problem-solving, and debugging skills.

Preferred (Bonus) Skills:

• Experience with custom MCP using FastMCP etc.
• Experience with FastAPI or similar frameworks for building scalable Python backends.
• Familiarity with React or other modern frontend frameworks.
• Understanding of cloud deployment environments (e.g., Docker, Kubernetes, AWS).
• Knowledge of LLM APIs from OpenAI, Anthropic, HuggingFace, etc.
• Exposure to CI/CD pipelines for deploying AI systems.