Job Description: Senior Python Generative AI Engineer - FastAPI, RAG & Agentic AI

Role: Python / Generative AI Engineer

Job Summary

We are looking for a skilled Python Generative AI Engineer with strong hands-on experience in Python development, API development, and AI-enabled workflows. The candidate will be responsible for designing, developing, deploying, and maintaining AI-powered applications using Python, FastAPI/Flask, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI frameworks.

The ideal candidate should have practical experience in prompt engineering, AI workflow development, and integrating Generative AI capabilities into enterprise applications. Exposure to Gemini LLM, machine learning frameworks, and NLP technologies will be an added advantage.

Key Responsibilities

• Design, develop, and maintain AI-enabled applications and workflows using Python.

• Build and integrate REST APIs using FastAPI and Flask frameworks.

• Develop and optimize Generative AI solutions using LLMs, RAG architecture, and Agentic AI concepts.

• Implement prompt engineering techniques to improve LLM response accuracy, relevance, and performance.

• Work with hybrid prompting techniques and apply suitable prompting strategies for different AI use cases.

• Develop and integrate AI workflows using frameworks such as LangChain, Hugging Face, and LlamaIndex.

• Integrate LLM services and Generative AI models into existing applications and enterprise systems.

• Deploy, monitor, and maintain AI models and applications across development, testing, and production environments.

• Perform code reviews, testing, debugging, and technical documentation.

• Follow best practices for version control, containerization, AI compliance, data privacy, and responsible AI.

• Stay updated with emerging Generative AI technologies, frameworks, and industry developments.

Required Technical Skills

• Strong hands-on programming experience in Python.

• Experience developing REST APIs using FastAPI and/or Flask.

• Experience in data processing and developing AI-enabled workflows using Python.

• Understanding of Large Language Models (LLMs), Prompt Engineering, RAG Architecture, and Agentic AI.

• Basic knowledge of hybrid prompting techniques.

• Experience with Generative AI frameworks and tools such as:

  • LangChain

  • Hugging Face

  • LlamaIndex

• Understanding of AI workflow development and LLM integration.

Good-to-Have Skills

• Hands-on experience with Gemini LLM.

• Knowledge of machine learning frameworks such as PyTorch, TensorFlow, and Keras.

• Understanding of Natural Language Processing (NLP).

• Experience with model deployment and containerization using Docker.

• Knowledge of version control systems such as Git.

• Awareness of AI compliance, data privacy, security, and Responsible AI principles.

Qualifications

• Bachelor's or Master's degree in Computer Science, Information Technology, Artificial Intelligence, or a related discipline.

• Strong analytical, problem-solving, and communication skills.

• Ability to work collaboratively with cross-functional technical teams.

• Willingness to continuously learn and adapt to evolving Generative AI technologies.