AI Engineer

IT Shoulders•San Jose, CA

About The Position

Develop and optimize generative AI applications using AWS Bedrock, LangChain, LangGraph, vector databases, large language models, embeddings, and retrieval-augmented generation (RAG). Build intelligent workflows and agents, integrate AI services with enterprise data and APIs, and collaborate with product managers, data scientists, and engineers to deliver AI-driven solutions. The role includes model evaluation, production safety and governance, performance optimization, and cost control.

Requirements

  • Hands-on experience with LangChain to develop intelligent workflows and GenAI applications.
  • Proficiency with LangGraph for advanced workflows, agents, state management, decision-making, and loops.
  • Experience with vector databases such as Qdrant, Pinecone, or FAISS, including retrieval optimization.
  • In-depth understanding of large language models, including GPT, BERT, and other transformer-based architectures, and their integration into applications.
  • Expertise in creating and integrating embeddings, using approaches such as sentence-BERT, OpenAI embeddings, or custom models.
  • Proven experience designing and implementing RAG systems.
  • Familiarity with Microsoft Cognitive Services, such as Azure Cognitive Search and Azure OpenAI, or other Microsoft AI tools.
  • Experience building or exposing Model Context Protocol resources, prompts, and tools to LLM-based agents.
  • Strong understanding of NLP techniques, including text classification, entity recognition, sentiment analysis, and summarization.
  • Experience with model fine-tuning, prompt engineering, and LLM optimization.
  • Familiarity with designing and consuming RESTful APIs and microservice architecture.
  • Problem-solving skills and an analytical mindset.
  • Teamwork and communication skills for cross-functional collaboration.

Nice To Haves

  • Experience with cloud platforms such as Azure, AWS, or Google Cloud, particularly deploying cloud-based AI solutions.
  • Knowledge of machine learning frameworks such as TensorFlow, PyTorch, or Hugging Face.
  • Data engineering skills, including preprocessing, cleaning, and augmenting large datasets.
  • Proficiency with Git and GitHub for version control, collaboration, and code review.
  • A degree in Computer Science, Data Science, AI, or a related field.
  • Experience building generative AI applications or platforms, including search systems and conversational AI.
  • Familiarity with LlamaIndex, FAISS, or similar vector search tools and libraries.

Responsibilities

  • Develop GenAI applications with LangChain, including chains, agents, and integrations.
  • Build workflow agents and decision-making systems with LangGraph, including state management and loops.
  • Design, implement, and maintain vector database solutions for storing and retrieving embeddings.
  • Integrate large language models into applications for conversational agents, summarization, content generation, and other use cases.
  • Create and integrate embeddings for text, images, and other media to support retrieval and search.
  • Design and implement RAG workflows that combine retrieval with language model generation.
  • Integrate Microsoft Cognitive Services and Model Context Protocol capabilities with AI applications and agents.
  • Evaluate and select foundation models based on latency, accuracy, and cost, using model evaluation and prompt routing.
  • Connect foundation models to enterprise data sources and vector stores using Bedrock Knowledge Bases.
  • Build multi-step workflows and agents using Bedrock Agents, Bedrock AgentCore, and AWS services such as Lambda, API Gateway, and Step Functions.
  • Configure safety, governance, logging, permissions, and optimization features for production AI systems.
  • Optimize models, embeddings, and retrieval systems for performance and efficiency.
  • Collaborate with product managers, data scientists, and engineers to understand business needs and deliver AI solutions.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service