Python - Open A.I Developer

Job Summary
Aquila360 is looking for a talented Python/OpenAI Developer to join our onsite team on a full-time basis. The ideal candidate will bring over three years of backend development experience with Python, along with at least two years dedicated to working on large language model (LLM) and AI-driven projects. This role centers on designing and implementing innovative generative AI features and applications using state-of-the-art technologies such as OpenAI, Claude, LangChain, and retrieval-augmented generation (RAG) pipelines. If you are passionate about building scalable AI solutions and enjoy leveraging the latest tools in the AI ecosystem, we invite you to apply and be part of our forward-thinking team.

Key Responsibilities
You will be responsible for developing and deploying generative AI solutions utilizing platforms like OpenAI, Claude, and Mistral. A significant part of your role will involve building and maintaining RAG pipelines, working with vector databases such as Pinecone, FAISS, and Weaviate to enhance data retrieval capabilities. You will implement LLM agent workflows using frameworks including LangChain, LangGraph, or AutoGen to create intelligent, responsive AI systems.

Designing and developing APIs for model inference using FastAPI or Flask will be essential to integrate AI models seamlessly into applications. You will also create AI-powered tools such as chatbots, document parsers, and data scrapers, handling diverse data formats including structured and unstructured types like PDFs, HTML, and audio files.

Optimizing prompt engineering to improve the efficiency and reliability of AI models will be a key focus. Additionally, you will integrate AI functionalities smoothly with frontend applications to ensure a cohesive user experience. Establishing CI/CD pipelines to automate AI model deployment and monitoring model performance for accuracy, scalability, and cost-effectiveness will round out your responsibilities.

Required Qualifications
Candidates must have a minimum of three years of backend development experience using Python. At least two years of hands-on experience building production-grade applications based on large language models is essential. Strong expertise in prompt engineering and token optimization techniques is required to maximize model performance.

Proficiency with OpenAI and Anthropic APIs, including experience in fine-tuning models, is critical. You should have practical knowledge of RAG pipelines and be familiar with vector database technologies. Experience working with frameworks like LangChain, LangGraph, or AutoGen is necessary to develop advanced LLM workflows.

Familiarity with cloud AI services such as AWS SageMaker, Azure OpenAI, or AWS Bedrock will be advantageous. You must demonstrate the ability to debug, scale, and deploy AI solutions effectively in production environments. Excellent communication skills and a collaborative mindset are essential to thrive within our team-oriented culture.

Preferred Qualifications and Benefits
We offer a competitive salary starting from Rs 150,000 per month, commensurate with experience. This full-time, onsite position provides the opportunity to work alongside a dynamic team focused on pioneering AI technologies. You will gain exposure to a broad range of AI tools and platforms, fostering continuous learning and professional growth.

Candidates should be prepared to discuss their last drawn salary and salary expectations during the application process. If you are a proactive and innovative developer eager to contribute to the future of AI applications, Aquila360 is the ideal place to grow your career.