Design and implement GenAI solutions leveraging LLMs, RAG pipelines, and Agentic AI architectures.
Develop and fine-tune deep learning models for NLP tasks using frameworks like PyTorch or TensorFlow.
Build scalable APIs using FastAPI to serve AI models and integrate with enterprise systems.
Collaborate with data scientists and ML engineers to deploy models using CI/CD pipelines on Azure.
Optimize model performance and ensure robustness in production environments.
Stay updated with the latest research and advancements in generative AI and deep learning.
Scalability & Performance: Ability to write efficient code and consider scalability and latency implications for Gen AI applications.
Containerization: Practical experience with Docker for packaging and deploying applications.
Key Skills, Experience & Knowledge:
(Must-Have)
Robust programming skills in Python with experience in building ML/NLP applications.
Hands-on experience with Deep Learning, Machine Learning, and Natural Language Processing.
Proficiency in working with LLMs (e.g., GPT,Gemini, LLaMA, Mistral) and RAG architecture.
Experience with Agentic AI frameworks and autonomous agent design.
Familiarity with FastAPI for building RESTful APIs.
Experience with CI/CD pipelines and deploying solutions on Azure Cloud, GCP and AWS
Solid understanding of data structures, algorithms, and software engineering principles.
Bachelor’s or master’s degree in computer science, AI, Data Science, or related field.
Retrieval Augmented Generation (RAG): Hands-on experience in building and optimizing RAG pipelines from scratch
Expert-level proficiency and hands-on experience with LangChain and/or LlamaIndex for building complex LLM applications, including chains, agents, memory, and tool integration