> Markdown version of [/jobs/ext/4802285-ai-engineer](https://www.wearedevelopers.com/jobs/ext/4802285-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI Engineer - **Company:** Cornerstone Barricades - **Location:** San Jose, CA, United States - **Contract:** Permanent contract - **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Automated Storage and Retrieval Systems, Microsoft Azure, Big Data, Cloud Computing, Code Review, Encodings, Databases, Data Cleansing, Information Engineering, Github, Identity and Access Management, Information Retrieval, Machine Learning, Natural Language Processing, Named Entity Recognition, Performance Tuning, Recommender Systems, OpenAI, Bedrock Knowledge Bases, Tensorflow, Sentiment Analysis, Software Engineering, Systems Integration, Data Logging, Pinecone, Qdrant, Google Cloud, Pytorch, LangChain, Retrieval-Augmented Generation, Large Language Models, Prompt Engineering, Model Validation, Llamaindex, AgentCore, Generative AI, Agentic-AI, Git, AI Platforms, Amazon Bedrock, HuggingFace, FAISS, Data Augmentation, Claude, Virtual Agents, Text Summarization, Api Gateway, Restful APIs, Model Context Protocol, Document Classification, GPT, Software Version Control, Natural Language Generation, Microservices - **Published:** November 20, 2026 - **Apply:** https://itshoulders.betterteam.com/ai-engineer/apply ## About the Role * Model Selection & Evaluation: Compares foundation models (such as Anthropic Claude, Amazon Nova, Llama, and Mistral) for latency, accuracy, and cost, using model evaluation and prompt routing. * RAG & Knowledge Bases: Connects foundation models to enterprise data sources and vector stores via Bedrock Knowledge Bases for grounded responses. * Agent & Workflow Engineering: Builds multi-step workflows and agents using Bedrock Agents, Bedrock AgentCore, and AWS services like Lambda, API Gateway, and Step Functions. * Safety, Governance & Optimization: Configures Bedrock Guardrails, IAM permissions, logging, prompt caching, and model distillation for production reliability and cost control. * LangChain: Hands-on experience with LangChain for developing intelligent workflows, managing chains, and leveraging its powerful capabilities for building GenAI applications. * LangGraph: Proficiency in LangGraph for designing advanced workflows and agents with state management, decision-making, and loops. * Vector Databases (e.g., Qdrant, Pinecone, FAISS): Experience working with vector databases to manage and search embeddings, and optimize large-scale retrieval tasks. * Large Language Models (LLMs): In-depth understanding of LLMs, such as GPT, BERT, and other transformer-based architectures, and how to integrate them into GenAI applications. * Embedding Creation and Integration: Expertise in building embeddings using models like sentence-BERT, OpenAI embeddings, or custom models for a variety of data types (text, images, etc.). * Retrieval-Augmented Generation (RAG): Proven experience in designing and implementing RAG systems that combine real-time retrieval with language model generation. * Microsoft Cognitive Platform (MCP): Familiarity with integrating Microsoft Cognitive Services, such as Azure Cognitive Search, Azure OpenAI, or other Microsoft AI tools, into GenAI applications. * Model Context Protocol (MCP) - Building or exposing Resources , Prompts , tools to LLM based AI Agents . * Natural Language Processing (NLP): Strong understanding of NLP techniques, including text classification, entity recognition, sentiment analysis, and text summarization. * AI Model Optimization: Experience in model fine-tuning, prompt engineering, and optimizing LLMs for specific tasks. * APIs & Microservices: Familiarity with designing and consuming RESTful APIs, and microservice architecture for scalable AI solutions. Additional Skills: * Cloud Platforms (Azure, AWS, GCP): Experience deploying GenAI applications on cloud platforms such as Azure, AWS, or Google Cloud, with an emphasis on cloud-based AI solutions. * Machine Learning Frameworks: Knowledge of popular ML frameworks, such as TensorFlow, PyTorch, or Hugging Face, and how to use them for model training and inference. * Data Engineering: Strong skills in handling large datasets, including data preprocessing, data cleaning, and data augmentation, to support AI model training. * Version Control: Proficiency with Git and GitHub for version control, collaborative development, and code review processes. * Problem-Solving & Analytical Thinking: Excellent problem-solving skills with a strong analytical mindset to break down complex AI challenges into manageable components. * Collaboration & Communication: Strong teamwork and communication skills to effectively collaborate with cross-functional teams and deliver high-impact solutions., * Advanced Degree: A degree in Computer Science, Data Science, AI, or a related field. * GenAI Application Development: Experience in building AI-driven applications or platforms with a focus on generative models, search systems, and conversational AI. * Familiarity with LlamaIndex, FAISS, or Similar Tools: Knowledge of popular vector search tools and libraries beyond LangChain and LangGraph is a plus. ## Description We are looking for an experienced and motivated AI Engineer to join our team in building cutting-edge applications powered by AI technologies. As a AI Engineer, you will work with LangChain, LangGraph, Vector Databases, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) to create intelligent, scalable, and efficient AI-driven applications. You will play a key role in integrating these advanced technologies into real-world use cases, including text generation, knowledge retrieval, and recommendation systems., * LangChain Development: Develop GenAI applications using LangChain, including building chains, agents, and integrations for a variety of use cases. * LangGraph Development: Utilize LangGraph for building workflow agents, controlling states, and developing intelligent decision-making systems. * Vector Database Integration: Design, implement, and maintain vector database solutions (e.g., Qdrant, Pinecone, FAISS) for efficient storage and retrieval of embeddings. * LLM Integration: Leverage LLMs to generate high-quality outputs for various use cases, such as conversational agents, document summarization, or content generation. * Embedding Building: Develop embeddings for text, images, and other media to integrate into retrieval systems and enhance search relevance and accuracy. * RAG Implementation: Design and implement RAG workflows to improve accuracy and context in AI applications by combining real-time retrieval with language model generation. * MCP Integration: Work with the Microsoft Cognitive Platform (MCP) for AI and cognitive services, integrating them with LangChain and LangGraph for enhanced capabilities. * Optimization & Fine-Tuning: Continuously optimize AI models, embeddings, and retrievers for performance and efficiency. * Collaboration & Problem-Solving: Work closely with product managers, data scientists, and other engineers to understand business needs and deliver AI-driven solutions.