AI Engineer | Onsite
Photon · United States
Role Summary:
AI Engineer with strong hands-on experience in prompt engineering, LLM response optimization, and AI application development. The ideal candidate can design prompts, improve model output quality, help LLMs understand user input, and build reliable, context-aware AI solutions.
Key Responsibilities
- Design, develop, and optimize prompts for Large Language Models (LLMs) to improve accuracy, reliability, and business outcomes.
- Build and configure Agentic AI solutions that leverage planning, reasoning, memory, and multi-step task execution capabilities.
- Develop and integrate MCP (Model Context Protocol) tools, enabling AIagents to securely discover and interact with enterprise systems, APIs, and data sources.
- Design agent architectures, tool-calling frameworks, retrieval mechanisms, and context management strategies.
- Collaborate with product managers, architects, and engineering teams to translate business requirements into AI-driven solutions.
- Implement Retrieval-Augmented Generation (RAG), knowledge grounding, and context orchestration patterns.
- Define evaluation frameworks and prompt testing methodologies to measure agent performance, quality, and reliability.
- Ensure AI solutions adhere to security, compliance, governance, and responsible AI standards.
- Support deployment, monitoring, troubleshooting, and continuous improvement of AI agents and MCP-enabled workflows.
- Contribute to architecture reviews, technical design documentation, and engineering best practices for AI platforms.
Required Skill
- Hands-on experience with LLMs such as GPT, Claude, Gemini, Llama, or similar models.
- Strong prompt engineering skills, including prompt templates, system prompts, few-shot prompting, and response tuning.
- Develop AI-powered applications using LLM APIs, RAG workflows, enterprise data sources, and backend services.
- Experience with LLM APIs and application integration using Python, Java, JavaScript, or similar programming languages.
- Knowledge of RAG, embeddings, vector databases, semantic search, and knowledge retrieval workflows.
- Ability to evaluate and improve AI responses for accuracy, relevance, completeness, tone, and instruction following.
- Understanding of NLP concepts, hallucination mitigation, prompt injection risks, guardrails, and responsible AI practices.
- Knowledge of healthcare data privacy and secure sensitive-data handling, including HIPAA-aligned PHI/PII practices, data minimization, de-identification, masking, access controls, auditability, and responsible use of healthcare data in AI workflows.
- Experience with MCP servers, cloud platforms, APIs, backend services, and production deployment is preferred.
- Experience integrating AI agents with healthcare, health records, or regulated industry systems.