Software Engineer (Python & Generative AI)

Job Description

Must Have Skills: Python Good to have : Generative AI Locations: Chennai/Pune Detailed JD : Position Summary: We seek an experienced Software Engineer with 7+ years of hands-on expertise in Python development and Generative AI technologies. The ideal candidate will design, develop, and deploy RESTful APIs and end-to-end GenAI solutions, driving innovation through experimentation in Jupyter notebooks, robust API development, and advanced prompt engineering across leading LLM platforms. Key Responsibilities: ? Develop and maintain REST APIs using Python frameworks such as FastAPI, Flask, or Django REST Framework ? Conduct prototyping and experimentation in Jupyter notebooks utilizing ML libraries including scikit-learn, TensorFlow, and PyTorch ? Architect and productionize Generative AI pipelines and workflows ? Design and optimize prompts, prompt templates, and chain-of-thought strategies for large language models (OpenAI, Anthropic, Hugging Face, etc.) ? Integrate vector databases and implement retrieval-augmented generation (RAG) and embedding-based solutions ? Containerize applications using Docker and manage deployments via Kubernetes or similar orchestration platforms ? Build and maintain CI/CD pipelines for both code and model artifacts using tools like GitLab CI/CD, GitHub Actions, or Cloud Build ? Monitor system performance, cost efficiency, accuracy, and ethical compliance; iterate on model evaluation metrics accordingly ? Mentor junior engineers on Python best practices, software design principles, and Generative AI methodologies Required Qualifications: ? Bachelor?s or Master?s degree in Computer Science, Engineering, or a related discipline ? Minimum 7 years of professional experience in Python software development ? Strong expertise in REST API design and development with FastAPI, Flask, or Django REST Framework ? Extensive experience using Jupyter notebooks for data exploration, prototyping, and model training ? Proficient with core machine learning libraries such as scikit-learn, TensorFlow, or PyTorch ? Demonstrated experience in prompt engineering and working with multiple large language model providers ? Solid understanding of vector embeddings, similarity search, and retrieval-augmented generation architectures ? Hands-on experience with Docker containerization and orchestration platforms like Kubernetes, Cloud Run, or ECS ? Proven track record in productionizing ML/AI systems including logging, tracing, metrics, and automated rollback mechanisms