Python Developer - AI & LLM Developer - Immediate Joiners Preferred

Job Description

Were looking for a skilled Python Developer with strong hands-on experience integrating and working with modern Large Language Models (LLMs) such as OpenAI , Claude , Amazon Titan , Gemini , and others. The ideal candidate will have deep experience in building, deploying, and fine-tuning LLM-powered features into real-world applications. This is a high-impact role for someone passionate about applying generative AI and LLMs to solve complex business problems. Role & responsibilities Design and develop Python-based APIs, scripts, and services that interact with LLMs like OpenAI GPT, Claude, Titan, Gemini, etc. Integrate LLMs into applications for use cases like text summarization, Q&A systems, semantic search, code generation, personalization, and workflow automation. Optimize prompt engineering, fine-tuning, and model orchestration for accuracy, performance, and cost. Implement robust error handling, logging, and monitoring for LLM-powered components. Collaborate with product teams, data scientists, and AI researchers to experiment with and evaluate different models and approaches. Stay up-to-date with advancements in AI/ML and contribute insights and improvements to our AI capabilities. Preferred candidate profile Joining in the next 15 days. 2+ years of professional Python development experience. Proven experience working with any one of the following LLMs: OpenAI (e.g., GPT-4/4o, embeddings) Claude (Anthropic APIs) Amazon Bedrock / Titan Google Gemini Strong understanding of RESTful APIs, asynchronous programming, and cloud-based deployments (AWS, GCP, or Azure). Experience with libraries like LangChain , LLM orchestration tools , or vector databases like Pinecone , Weaviate , or FAISS . Familiarity with prompt engineering and prompt chaining techniques. Experience in data processing, NLP pipelines, and working with JSON, YAML, or XML. Excellent problem-solving skills and a collaborative mindset. Nice-to-Have Skills Experience with front-end frameworks or full-stack development (e.g., React, Flask/FastAPI). Experience with RAG (Retrieval Augmented Generation) systems. Background in ML model evaluation, vector embeddings, and semantic search. Contributions to open-source AI projects or published work in the LLM domain.