GenAI Technical Architect

Job Description :

We are seeking a visionary GenAI Technical Architect to lead the design and deployment of cutting-edge Generative AI (GenAI) and Large Language Model (LLM)-based systems. Youll play a pivotal role in shaping intelligent applications, creating agentic systems, and orchestrating scalable solutions that unlock new frontiers in human-computer interaction and enterprise intelligence.

Responsibilities :

- Design intelligent agents with capabilities like memory, tool use, and contextual orchestration

- Integrate embedding models, FAISS/Pinecone-based vector search, and knowledge retrieval systems

- Lead model deployment using frameworks such as TGI, vLLM, or OpenLLM

- Build scalable, cloud-native architectures on AWS, GCP, or Azure

- Collaborate with cross-functional teams to design APIs and containerized services using Docker and Kubernetes

- Evaluate LLM capabilities and limitations to guide solution design and implementation

- Define GenAI best practices and contribute to internal knowledge-sharing effort

Required Skills :

- Good expertise in Python, FAST API, AI,ML Concepts (Text Preprocessing, Vector Embedding, etc..)

- Deep understanding of LLMsincluding capabilities, limitations, fine-tuning, and prompt engineering

- Strong grasp of agentic architecture principles, including tools, memory modules, and workflow orchestration

- Hands-on experience with vector search technologies (e.g., FAISS, Pinecone) and embedding techniques

- Practical experience deploying models with frameworks like TGI, vLLM, and OpenLLM

- Proficiency in designing and deploying solutions in cloud environments (AWS, GCP, or Azure)

- Expertise in API architecture and containerization using Docker and Kubernetes

- Excellent communication skills and a collaborative mindset

Desired Skills :

- Familiarity with privacy and ethical AI frameworks

- Contributions to open-source GenAI projects

Education : B.Tech/M.Tech/MCA