Mandatory Skills: LLM, Redis Vector Database, Azure OpenAI, Python, Fast API, Docker, Kubernetes, RAG, Agents, Graphs, Fine tuning of LLMs, AI/ML framework, ML flow, Gen-AI In the role of a Data Scientist (ML), you will operate at the intersection of: LLM-based frameworks, tools, and technologies, Cloud-native technologies and solutions, Microservices-based software architecture and design patterns, Domain specific fine tuning/Prompting of use cases, Working knowledge of structured and unstructured retrieval-based architectures. As an additional responsibility, you will be involved in the complete development cycle of new product features, encompassing tasks such as the development and deployment of new models integrated into production systems. Furthermore, you will have the opportunity to critically assess and influence the product engineering, design, architecture, and technology stack across multiple products, extending beyond your immediate focus.
Responsibilities
1. Design, develop, and implement innovative Language Model applications using Azure OpenAI and Redis as a vector database. 2. Collaborate with cross-functional teams to integrate LangChain, OpenAI Python SDK, LammaIndex, OLamma, and other technologies into the application architecture. 3. Implement and optimize machine learning models for natural language processing tasks. 4. Ensure the scalability, performance, and reliability of language model applications. 5. Collaborate with data scientists, software engineers, and other stakeholders to enhance and refine language models based on user feedback and evolving requirements. 6. Stay current with industry trends and advancements in language models, AI, and related technologies. 7. Working knowledge of Fast API, Celery and Docker
Requirements
1. Bachelor's or master's degree in engineering, or related field with 1-3 years of work experience. 2. Proven experience in developing and deploying applications utilizing Azure OpenAI and Redis as a vector database. 3. Solid understanding of language model technologies, including LangChain, OpenAI Python SDK, OLamma, etc. 4. Proficiency in implementing and optimizing machine learning models for natural language processing. 5. Experience with observability tools such as mlflow, langsmith, langfuse, weight and bias, etc. 6. Conceptual understanding of working principle of LLMs and fine tuning of LLMs. 7. Proven application of RAG, Agents, Graphs to orchestrate production grade LLM applications. 8. Strong programming skills in languages such as Python and proficiency in relevant frameworks. 9. Familiarity with containerization and orchestration tools (e.g., Docker, Kubernetes). 10. Excellent problem-solving and communication skills. 11. Industry experience in Marketing is a good to have.