Senior Generative AI Developer - RAG/LLM (5-7 yrs)

Job Requirement :

We are seeking a highly skilled Senior Generative AI Developer to join our AI/ML team. This role focuses on leveraging cutting-edge Generative AI (GenAI) technologies to drive innovation and efficiency in software development and business processes. The ideal candidate will work on advanced techniques such as Retrieval-Augmented Generation (RAG), document chunking, and data embedding across multiple vector databases. They will collaborate closely with cross-functional teams to design, implement, and optimize AI-driven solutions, with exposure to cloud-native AI platforms like Amazon Bedrock and Microsoft Azure OpenAI considered a plus.

Responsibilities :

- Develop and deploy GenAI-based applications to solve complex business problems.

- Implement RAG frameworks to enhance information retrieval and response accuracy.

- Design and optimize document chunking strategies tailored to specific data types and use cases.

- Build and manage data embeddings using various vector databases for high-performance similarity searches.

- Collaborate with data engineers and scientists to integrate AI solutions seamlessly into existing pipelines.

- Explore and implement best practices for leveraging Amazon Bedrock and Azure OpenAI services.

- Stay updated on emerging trends and technologies in the GenAI and AI/ML landscape.

Mandatory Skills :

- Proficiency in Generative AI frameworks and technologies like

a. Prompt Engineering - creating specific prompts to guide LLM outputs

b. Fine Tuning and Few-Shot learning - Adapting LLMs for domain-specific tasks.

c. Retrieval-Augmented Generation (RAG) - Combining LLMs with external data retrieval systems

d. Text-to-Text Transfer Transformation (T5) - Framework for translating tasks into text forms.

- Expertise in designing and implementing chunking strategies for diverse datasets.

- Strong knowledge of data embedding techniques and working experience with vector databases like Pinecone, Weaviate, or Milvus.

- Solid programming skills in Python, with experience in AI/ML libraries such as TensorFlow, PyTorch, or Hugging Face Transformers.

- Familiarity with cloud platforms and services for AI/ML workloads (AWS or Azure).

- Experience with API integration for AI services and building scalable applications.

Desirable Skills :

- Hands-on experience with Amazon Bedrock and/or Microsoft Azure OpenAI services.

- Knowledge of natural language processing (NLP) techniques and large language model (LLM) fine-tuning.

- Exposure to different chunking strategies, including overlap and semantic segmentation.

- Understanding of DevOps practices for deploying and managing AI models in production.

- Strong problem-solving and analytical skills with a focus on delivering value-driven solutions.

Years of Experience :

- Overall experience - 5 to 7 years

- Hands-on experience in Python - 4 to 5 years

- AI/ML experience - 3 to 4 years

- GenAI experience (good to have) - 1 to 2 years