Job description
About the Role
We are looking for a passionate and driven AI Engineer (Intern/Fresher/Experienced) with hands-on experience or strong academic exposure in RAG (Retrieval-Augmented Generation) approaches. You will work closely with our AI and product teams to design, prototype, and optimize intelligent solutions that integrate language models with structured/unstructured knowledge sources. This is a great opportunity to build impactful AI systems and work with up-to-date NLP tools in real-world production environments.

Responsibilities
- Design and build AI applications using RAG-based architecturesFine-tune and integrate LLMs (eg, OpenAI, LLaMA, Mistral, etc) with external data sources
- Build and optimize pipelines for document ingestion, chunking, vector embedding, and retrieval
- Implement and experiment with tools like LangChain, Haystack, Weaviate, Pinecone, Chroma, FAISS
- Develop and maintain RESTful APIs and web applications using Python frameworks such as Flask or FastAPI
- Collaborate with frontend/backend teams to integrate AI into live products




- Conduct evaluations, benchmark performance, and recommend improvements
- Work with team leads to convert PoCs into scalable solutions

For Experienced (2+ Years):
- Proven experience in building or contributing to AI products using RAG architecture
- Strong proficiency in Python for data manipulation and API development
- Experience in RESTful API development using Flask or FastAPI
- Solid knowledge of SQL, data analytics, and Power BI
- Hands-on experience with version control (Git) and deployment tools
- Exposure to cloud platforms such as AWS is a strong plus
- Excellent problem-solving and communication skills

What You'll Gain
- Opportunity to work on cutting-edge AI projects with real-world users
- Exposure to both product delivery and research-level challenges
- Mentorship from experienced AI Engineers and Product Leads
- Flat team structure, creative freedom, and a learning-oriented culture

📌 AI Engineer (Delhi)
🏢 taxmann
📍 Delhi