GenAI Architect

Overview

Remote
Depends on Experience
Accepts corp to corp applications
Contract - W2
Contract - Independent
Contract - 6 Month(s)

Skills

Design
develop
and deploy GenAI solutions

Job Details

Responsibilities for Internal Candidates

* Design, develop, and deploy GenAI solutions including RAG systems and agentic orchestration by integrating vector stores and cloud AI services (AWS SageMaker/Bedrock, Azure OpenAI, Google Cloud Platform Vertex AI).

* Implement and optimize transformer-based models (LLMs) for advanced NLP use cases, such as dynamic document retrieval, summarization, question answering and conversational agents.

* Collaborate with cross-functional teams to integrate GenAI services (APIs, microservices) into enterprise applications and automate workflows for content generation and analysis.

* Develop end-to-end automation pipelines using GenAI orchestration frameworks (LangChain, Autogen, Haystack) and manage vector embeddings, metadata stores, and retrieval layers.

* Monitor retrieval performance, model quality (accuracy, latency, hallucination rates) and user feedback loops to continuously refine prompt templates, embedding configurations, and agent policies.

* Stay updated with the latest advancements in GenAI architectures, vector database innovations, multi-agent strategies, and emerging frameworks like LangGraph and Autogen.

* When required, design and develop deterministic python code to augment LLM based solutions, based on usecases

Qualifications for Internal Candidates

* Passionate about advanced GenAI capabilities, including RAG, vector similarity search, and agentic system design.

* 5+ years of AI/ML development experience, with at least 2 years focused on building and deploying GenAI solutions.

* Proficiency deploying and orchestrating LLM-based pipelines on cloud AI platforms (AWS SageMaker/Bedrock, Azure OpenAI, Google Vertex AI) and managing associated infrastructure.

* Strong knowledge of core ML frameworks (TensorFlow, PyTorch) and GenAI-specific toolkits (Hugging Face Transformers, OpenAI API, LangChain, Autogen, Haystack).

* Experience developing and implementing python APIs or functions

* Proven experience building retrieval-augmented generation systems, fine-tuning LLMs for domain adaptation, and implementing prompt-engineering best practices.

* Excellent problem-solving skills and ability to work in an agile development environment.

* Strong communication skills to collaborate with technical and non-technical teams.

Preferred Qualifications:

* Experience designing agentic multi-agent GenAI workflows using frameworks like LangGraph and applying reinforcement learning for LLM-driven decision making.

* Experience developing GenAI applications for automated document ingestion, processing, summarization, or enterprise email routing.

* Familiarity with API development, microservices architecture, and containerization (Docker, Kubernetes).

Employers have access to artificial intelligence language tools (“AI”) that help generate and enhance job descriptions and AI may have been used to create this description. The position description has been reviewed for accuracy and Dice believes it to correctly reflect the job opportunity.