AI Implementation Engineer - Python Specialization

• Develop and maintain scalable Python services that implement AI-powered retrieval and generation workflows
• Build and optimize vector-based retrieval pipelines using tools like FAISS, Pinecone, or Weaviate
• Integrate LLMs via APIs (e.g., OpenAI, Hugging Face) using orchestration frameworks such as LangChain, LlamaIndex, etc.
• Collaborate on system architecture, API design, and data flow to support RAG systems
• Monitor, test, and improve the performance and accuracy of AI features in production
• Work in cross-functional teams with product, data, and ML stakeholders to deploy AI solutions quickly and responsibly

• Expert in Core Python with clean, modular, and maintainable code practices
• Proficient in building RESTful APIs using Django Rest Framework (DRF)
• Strong experience with relational databases like PostgreSQL/MySQL, including Django ORM and SQL optimization
• Skilled in designing and implementing complex, large-scale features with solid architectural decisions
• Solid grasp of OOP principles, data structures, and design patterns
• Hands-on experience with Git, Linux/Unix commands, and effective debugging techniques
• Experience integrating Large Language Models (LLMs) and AI/ML capabilities into applications
• Familiarity with LangChain, LlamaIndex, and vector databases like FAISS, Pinecone, or Weaviate
• Knowledge of Information Retrieval (IR), semantic search, and embedding models
• Understanding of prompt engineering, tokenization, and LLM fine-tuning workflows (preferred)

Understanding of prompt engineering, tokenization, and LLM fine-tuning workflows

• Best in class packages
• Paid holidays and flexible paid time away
• Casual dress code & flexible working environment
• Medical Insurance covering self & family up to 4 lakhs per person