Generative AI Engineer

Bright Vision Technologies • Irving, TX

1d • $115,000 - $165,000 • Remote

About The Position

Bright Vision Technologies is seeking a Generative AI Engineer to design and develop applications powered by large language models and other generative models. The role implements retrieval-augmented generation, prompt and response workflows, model evaluation, and application integrations while addressing accuracy, latency, cost, observability, and responsible-use requirements.

This is a remote, full-time, direct W2 position. Bright Vision Technologies is unable to sponsor new H-1B visa petitions for this position; U.S. Citizens, Green Card holders, EAD holders, and H-1B transfer candidates are encouraged to apply.

Requirements

• Typically 5+ years in software engineering or applied AI, with hands-on generative AI development; align with the approved requisition.
• Strong Python programming and experience developing APIs or production application services.
• Hands-on experience with large language model APIs, prompt engineering, and structured model responses.
• Understanding of embeddings, vector search, document retrieval, and retrieval-augmented generation concepts.
• Experience with data processing, API integration, testing, version control, and application deployment practices.
• Ability to evaluate model responses and address reliability, latency, cost, and data-quality considerations.
• Strong problem-solving and communication skills with attention to responsible AI implementation.
• Experience working in iterative software delivery teams.

Nice To Haves

• Experience with LangChain, LlamaIndex, Semantic Kernel, or comparable orchestration tools.
• Familiarity with vector databases, reranking, model evaluation frameworks, and prompt versioning.
• Exposure to cloud AI services, containerization, and scalable inference architectures.
• Relevant generative AI or cloud AI certification.

Responsibilities

• Build generative AI application components using approved foundation models, model APIs, and orchestration frameworks.
• Develop retrieval-augmented generation workflows using document ingestion, chunking, embeddings, and vector retrieval.
• Design prompts, structured outputs, tool integrations, and conversation workflows for defined application use cases.
• Create evaluation datasets and assess answer quality, relevance, hallucination risk, latency, and cost.
• Integrate AI capabilities with enterprise systems and implement logging, monitoring, fallback, and feedback mechanisms.
• Participate in planning, defect triage, and release validation as appropriate to the assignment.

What This Job Offers

• Job Type: Full-time
• Education Level: No Education Listed