Senior AI Engineer: LLM Prompts, Agentic AI

Photon; Dallas (TX); Sur place; USD 120 000 - 180 000; Plein temps

Résumé du poste

Photon is seeking an AI Engineer to design, build, and optimize prompts and AI-driven solutions for enterprise contexts. You will implement MCP-enabled workflows, secure data handling, and knowledge-grounded architectures across regulated environments.

The role emphasizes hands-on development with LLMs, RAG, and tool-calling patterns, collaborating with product and engineering to deliver reliable AI platforms.

Qualifications

• Hands-on experience with prompt engineering for LLMs.
• Experience designing prompts, system prompts, few-shot prompts and tuning.
• Develop AI-powered apps using LLM APIs and RAG workflows.
• Knowledge of HIPAA-aligned data privacy and secure handling.

Responsabilités

• Design, develop, and optimize prompts for LLMs to improve accuracy and outcomes.
• Build Agentic AI solutions using planning, reasoning, memory, and multi-step execution.
• Develop MCP tools to securely interact with enterprise data sources.
• Design architectures, tool-calling frameworks, and context management strategies.
• Collaborate with product, architects, and engineering to translate requirements into AI solutions.
• Implement retrieval-augmented generation and knowledge grounding patterns.
• Define evaluation and testing for agent performance and reliability.
• Ensure AI solutions meet security, governance, and responsible AI standards.
• Support deployment, monitoring, troubleshooting, and continuous improvement of AI agents.
• Contribute to design documentation and engineering best practices for AI platforms.

Connaissances

Prompt engineering

LLM APIs

RAG workflows

Knowledge retrieval

NLP fundamentals

HIPAA security

Outils

MCP servers

Vector databases

Semantic search

Description du poste

Photon is seeking an AI Engineer to design, build, and optimize prompts and AI-driven solutions for enterprise contexts. You will implement MCP-enabled workflows, secure data handling, and knowledge-grounded architectures across regulated environments.

The role emphasizes hands-on development with LLMs, RAG, and tool-calling patterns, collaborating with product and engineering to deliver reliable AI platforms.