Logo
Aptino, Inc.

GenAI Design Architect (Santa Clara County)

Aptino, Inc., Santa Clara, California, United States

Save Job

Role:

GenAI Design Architect Location:

Santa Clara County, California, United States (Onsite) Duration:

12 months

We are looking for a skilled

AI Architect

with strong expertise in

OpenAI technologies, Python development, and building AI-driven applications . The ideal candidate should have hands-on experience in designing, developing, and deploying LLM-based solutions, integrating OpenAI APIs, and working with machine learning pipelines.

Key Responsibilities Design, develop, and implement AI/LLM-based solutions using

OpenAI models (GPT, Embeddings, Assistants, Vector Stores, Fine-tuning) . We are seeking a Generative AI (GenAI) Design Engineer to join our team and drive innovation in AI-powered solutions. Build robust, scalable

Python applications

integrating OpenAI APIs and other GenAI frameworks. Develop end-to-end pipelines for

prompt engineering, data preprocessing, model evaluation, and deployment . Collaborate with product and engineering teams to identify AI use cases and deliver production-ready solutions. Optimize model performance, latency, and cost using best practices. Create tools, scripts, and automations for AI workflows (e.g., embeddings, RAG systems, chatbots). Ensure AI systems follow security, compliance, and ethical guidelines. Maintain documentation, architecture diagrams, and code quality standards. Required Skills & Qualifications Bachelors or Masters degree in Computer Science, Engineering, AI/ML, or related field. 26 years

of experience as an AI Engineer / ML Engineer / Python Developer. Strong programming proficiency in

Python

and related libraries (FastAPI, Flask, Pandas, NumPy). Hands-on experience with

OpenAI APIs , including GPT models, Assistants, Function Calling, Fine-tuning, and Embeddings. Experience building

LLM-based applications , such as chatbots, RAG systems, classification tools, automation agents, or content generation engines. Familiarity with vector databases (Pinecone, ChromaDB, FAISS, Weaviate). Knowledge of cloud platforms ( AWS, Azure, GCP ) and containerization (Docker). Understanding of ML fundamentals: NLP, model evaluation, prompt engineering. Strong problem-solving, analytical, and communication skills.