Job Summary
Key Responsibilities
• Understanding on how to Design and Build GenAI Solutions: Collaborate on the end-to-end development of Generative AI applications, including system design, model integration, and back-end logic.
• Implement Advanced RAG Pipelines: Engineer and optimize sophisticated Retrieval-Augmented Generation (RAG) systems. This includes selecting appropriate embedding models, setting up and managing vector databases, and refining context retrieval and ranking strategies to ensure response accuracy and relevance.
• Manage Application Architecture: Take ownership of the technical architecture for various GenAI use cases, ensuring they are scalable, reliable, and efficient.
• Collaborate and Innovate: Work closely with the Lead Engineer to brainstorm new ideas, experiment with emerging technologies, and continuously improve our existing solutions.
• Stay Current: Keep up-to-date with the latest advancements in the rapidly evolving field of Generative AI and advocate for the adoption of best practices and new technologies.
Required Skills and Qualifications
Should be having overall experience of 5 years in Python,GenAI tools (Langchain, Langgraph)
Proficiency in Python, TensorFlow and PyTorch
• Proven GenAI Experience: Demonstrable experience building and deploying applications that leverage Large Language Models (e.g., OpenAI GPT series, Llama, Gemini, Claude).
• Strong Python Proficiency: Expertise in Python and core AI/ML libraries such as LangChain, LlamaIndex, Hugging Face, and PyTorch/TensorFlow.
• Deep RAG Expertise: A thorough, hands-on understanding of the entire Retrieval-Augmented Generation (RAG) architecture and workflow. You must be able to explain how context is ingested, retrieved, and utilized to mitigate model hallucinations along with different RAG chunking patterns and such.
• Vector Database Knowledge: Practical experience with vector stores like Pinecone, Weaviate, Chroma, or similar technologies.
AI Agent Frameworks Incorporate AI agent frameworks (e.g., LangChain, AgentGPT, or similar) to enable autonomous or semi-autonomous decision-making within applications.
Experience in deploying AI models into production environment
• Strong Problem-Solving Skills: Ability to tackle complex technical challenges independently and collaboratively.
Preferred Qualifications
• Experience with developing multi-agent systems using frameworks like AG2 or CrewAI or any other framework.
• Familiarity with LLM fine-tuning techniques (e.g., LoRA).
• Experience with Azure and their associated AI/ML services.
• A portfolio of GenAI projects (e.g., GitHub repository) is a strong plus.
• Excellent communication skills and a collaborative mindset.