Full Stack Developer

Overview:

We are looking for a passionate GenAI Developer with 2–3 years of software development experience and hands-on exposure to Generative AI technologies. The ideal candidate should have experience building AI-powered applications using Large Language Models (LLMs), prompt engineering, Retrieval-Augmented Generation (RAG), AI agents, and modern AI frameworks.

Key Responsibilities:

• Design, develop, and deploy Generative AI applications using LLMs such as GPT, Claude, Gemini, or Llama.
• Build intelligent AI assistants, chatbots, copilots, and workflow automation solutions.
• Develop and optimize RAG pipelines using vector databases and embedding models.
• Integrate AI models with web applications through REST APIs and SDKs.
• Design effective prompts and evaluate model performance for different business use cases.
• Fine-tune or customize open-source LLMs where required.
• Work with AI orchestration frameworks such as LangChain, LangGraph, LlamaIndex, or similar.
• Develop AI agents capable of tool calling and multi-step reasoning.
• Optimize model response quality, latency, scalability, and cost.
• Collaborate with product managers, designers, and backend/frontend developers to deliver AI-powered products.
• Stay updated with the latest developments in Generative AI and recommend improvements.

Required Skills:

• 2–3 years of software development experience.
• Strong proficiency in Python.
• Hands-on experience with OpenAI APIs, Azure OpenAI, Anthropic Claude, Google Gemini, or open-source LLMs.
• Experience with Prompt Engineering and Retrieval-Augmented Generation (RAG).
• Knowledge of LangChain, LangGraph, LlamaIndex, or similar AI orchestration frameworks.
• Experience with vector databases such as Pinecone, ChromaDB, Weaviate, FAISS, Milvus, or Qdrant.
• Familiarity with embedding models and semantic search.
• Experience building REST APIs using FastAPI or Flask.
• Knowledge of SQL and NoSQL databases.
• Familiarity with Git, Docker, and cloud platforms (AWS, Azure, or GCP).
• Strong debugging, analytical, and problem-solving skills.

Preferred Skills

• Experience with AI agents and autonomous workflows.
• Knowledge of model fine-tuning (LoRA, PEFT) and Hugging Face ecosystem.
• Experience with multimodal AI (text, image, audio, vision).
• Knowledge of MLOps, model deployment, and monitoring.
• Experience with React or other frontend frameworks is an added advantage.
• Understanding of AI safety, evaluation, and responsible AI practices.

Qualification

• Bachelor’s degree in computer science, Information Technology, Artificial Intelligence, or a related field.
• Relevant certifications in AI, Machine Learning, or Cloud platforms are preferred.