Project Role : LLM Model Developer
Project Role Description : Fine-tunes Large Language Models with emphasis on instruction fine-tuning and domain adaptation to enhance model relevance and performance in specific contexts.
Must have skills : Large Language Models (LLMs)
Good to have skills : NA
Minimum
7.5 year(s) of experience is required
Educational Qualification : 15 years full time education
Role Summary
Own end-to-end NLP & Generative AI solution development from design to production deployment. The role focuses on building scalable, cloud-native LLM-powered applications on Azure, including chatbots, AI assistants, and Retrieval-Augmented Generation (RAG) systems. The position also involves developing backend APIs, managing AI model integrations, deploying enterprise-grade AI solutions, and delivering rapid PoCs and MVPs while supporting team delivery and mentoring junior team members.
Key Responsibilities
- Develop and deploy LLM-powered chatbots, AI assistants, and RAG-based solutions
- Design and manage data ingestion, preprocessing, and document update pipelines
- Implement prompt engineering, embeddings, vector search, and model evaluation techniques
- Build and maintain asynchronous REST APIs using FastAPI and Flask
- Handle rate limiting, retries, fault tolerance, and load balancing for LLM APIs
- Deploy, monitor, and optimize AI applications on Azure Cloud platforms
- Deliver rapid PoCs and MVPs within tight timelines
- Collaborate with cross-functional teams to support project delivery
- Mentor junior developers and contribute to technical best practices
Must-Have Skills
- Advanced proficiency in Python
- Strong experience in NLP and Generative AI technologies (LLMs, RAG, prompt engineering)
- Hands-on expertise with Azure OpenAI and other LLM platforms
- Experience building async APIs using FastAPI or Flask
- Strong understanding of Azure Cloud services:
- Azure App Service
- Azure Storage
- Azure AI Search
- Azure Cosmos DB
- Experience with CI/CD pipelines, logging, and monitoring tools such as Jenkins and OpenTelemetry
Experience Required
- 5+ years of experience in NLP, AI, or Machine Learning
- Proven experience deploying and managing production-grade Generative AI solutions
