> Markdown version of [/jobs/ext/3779002-gen-ai-architect](https://www.wearedevelopers.com/jobs/ext/3779002-gen-ai-architect). 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).

---

# Gen AI Architect

- **Company:** InfoDyne Solutions LLC
- **Location:** New York, NY, United States
- **Contract:** Contract
- **Skills:** LangGraph Framework, Artificial Intelligence, Amazon Web Services, Microsoft Azure, Cloud Computing, Continuous Integration, Decision Support Systems, DevOps, Elasticsearch, Github, Python (Programming Language), Knowledge Management, Knowledge-Based Systems, NoSQL, Performance Tuning, OpenAI, Search Technologies, SQL Databases, Data Logging, Pinecone, Google Cloud, Chatbots, Data Ingestion, LangChain, Retrieval-Augmented Generation, Flask (Web Framework), Large Language Models, Multi-Agent Systems, Prompt Engineering, Generative AI, Agentic-AI, Fastapi, Gitlab-ci, Kubernetes, Information Technology, CrewAI, Weaviate, AutoGen, Milvus, Machine Learning Operations, FAISS, Claude, Invoking Functions, Google Gemini, Restful APIs, Terraform, Semantic Kernel, Intelligent Document Processing, GPT, Data Pipelines, OpenSearch, Docker, Jenkins, ChromaDB, Microservices
- **Published:** October 16, 2026
- **Apply:** https://www.dice.com/job-detail/8cdc6fbd-fd6f-4154-8d08-ef4587537de2

## About the Role

* Bachelor's or Master's degree in Computer Science, Engineering, Artificial Intelligence, or a related field, or equivalent practical experience.
 * Strong expertise in Generative AI and LLMs, including OpenAI GPT, Claude, Gemini, Llama, or Mistral, with knowledge of prompt engineering, fine-tuning, function calling, tool integration, agent orchestration, context management, and memory handling.
 * Proficiency in Python and experience building REST APIs, microservices, and enterprise integrations using FastAPI or Flask.
 * Practical experience with RAG architecture, vector databases, embedding models, semantic and hybrid search, and document ingestion pipelines, using technologies such as Pinecone, Weaviate, ChromaDB, FAISS, Milvus, Elasticsearch, or OpenSearch.
 * Knowledge of Docker, Kubernetes, CI/CD, GitHub Actions, Jenkins, GitLab CI, Terraform, and cloud platforms such as AWS, Azure, or Google Cloud Platform. Familiarity with MLOps, model deployment, monitoring, logging, AI governance, security, SQL/NoSQL databases, and data pipelines. Strong communication, problem-solving, and stakeholder management skills.

## Description

* Lead the architecture, design, and implementation of enterprise GenAI platforms and applications.
 * Design Agentic AI and multi-agent workflows using LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, or Llama Index.
 * Build and optimize RAG pipelines, vector search solutions, embedding workflows, and enterprise knowledge systems.
 * Develop AI solutions for business process automation, knowledge management, intelligent document processing, conversational AI, decision support, and developer productivity.
 * Build scalable APIs and microservices using Python, FastAPI, or Flask.
 * Implement AI monitoring, observability, security, governance, guardrails, and responsible AI practices.
 * Optimize prompts, context management, model performance, latency, reliability, and cost.
 * Drive cloud deployment, CI/CD, DevOps, and MLOps practices.
 * Collaborate with stakeholders to identify AI opportunities and translate business needs into scalable solutions.
 * Mentor engineering teams and establish enterprise AI best practices.