Gen AI Principal/Tech Lead Engineer - Python, FAST API

This role is focused on building real-world GenAI solutions - not just experimentation or research. The candidate should be comfortable writing production-quality code, building APIs, integrating LLMs, and working with modern AI engineering frameworks and cloud platforms. You will work closely with product managers, architects, data scientists, and engineering teams to develop scalable, secure, and efficient AI-powered applications.

• Design, develop, and deploy Generative AI applications using Large Language Models (LLMs) and modern AI frameworks.
• Build and maintain scalable backend services and REST APIs using Python frameworks such as FastAPI, Flask, or Django.
• Implement Retrieval-Augmented Generation (RAG) pipelines and semantic search solutions using vector databases.
• Integrate commercial and open-source LLMs into enterprise applications.
• Develop prompt engineering workflows and support AI model evaluation and optimization.
• Deploy and support AI applications on AWS cloud platforms.
• Participate in troubleshooting and optimizing AI systems for latency, reliability, scalability, and cost efficiency.
• Collaborate with cross-functional teams across onshore and offshore locations.
• Write clean, maintainable, and testable code following software engineering best practices.
• Participate in code reviews, unit testing, integration testing, and CI/CD processes.
• Stay updated on emerging trends and technologies in Generative AI and applied machine learning.
• 8 years of experience in software engineering, AI/ML, or related technical roles.
• Strong hands-on programming skills in Python.
• Experience building backend applications and REST APIs using FastAPI, Flask, or Django.
• Practical experience working with Generative AI or LLM-based applications.
• Understanding of Retrieval-Augmented Generation (RAG) concepts and semantic search.
• Experience with vector databases such as Pinecone, OpenSearch, or similar technologies.
• Experience integrating AI models or services such as OpenAI, Anthropic, AWS Bedrock, Hugging Face, or open-source LLMs.
• Experience with AWS cloud services and deploying applications in cloud environments.
• Understanding of software engineering best practices including:

o Unit testing

o Integration testing

o Git/version control

o CI/CD workflows

• Strong debugging, analytical, and problem-solving skills.
• Good communication and collaboration skills.

Must have Qualifications

• Experience with prompt optimization and AI evaluation techniques.
• Exposure to NLP