AI Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Develop and deliver production features powered by LLM and agentic technologies.

• Create prompt orchestration, tool invocation, embeddings, and structured outputs leveraging reusable components.

• Construct API integrations, MCP servers, and workflows for retrieval-augmented generation.

• Integrate existing data systems with vector search to ensure AI features accurately retrieve and explain published ratings data and cite sources.

• Establish and maintain evaluation infrastructure, including prompt regression tests, LLM-as-a-judge evaluations, and synthetic datasets.

• Oversee AI features in production and monitor accuracy, latency, token costs, and hallucination rates.

• Troubleshoot and refine prompts based on insights gained in production.

• Enforce runtime safety and reliability measures.

• Investigate and propose orchestration frameworks, vector stores, and model providers.

• Collaborate directly with non-technical stakeholders to define problems and evaluate AI capabilities.

• Assess emerging models and tools while utilizing AI-assisted development.

• Contribute to engineering standards through code reviews.

• Report directly to the VP of Engineering and work alongside senior engineers on system architecture, technical direction, and strategic AI initiatives.

• Assume ownership of AI features from the outset and progressively take on greater architectural responsibilities.

⛳️ Requirements

• 2-3+ years of experience in building or deploying machine learning models or AI-driven applications.

• Bachelor’s degree in Computer Science, Engineering, AI/ML, or a related discipline, or relevant certification.

• Equivalent technical proficiency and industry experience may substitute for a formal degree.

• At least 2 years of experience in Python, either professionally or through significant project involvement.

• Strong understanding of fundamental machine learning concepts and API integration.

• Practical experience with foundation model providers such as Anthropic, OpenAI, or similar.

• Background in prompt engineering and agentic methodologies.

• Familiarity with orchestration frameworks like LangChain or LlamaIndex, or integration standards such as the Model Context Protocol.

• Experience in querying and tuning vector databases like pgvector, OpenSearch, or similar for RAG applications.

• AWS proficiency is required.

• Experience with managed cloud AI services like Amazon Bedrock is preferred.

• Familiarity with cloud deployment of application code using serverless or containerized approaches is preferred.

• Experience with Scrum or other Agile methodologies is preferred.

• Cloud, Gen AI, or machine learning certifications are preferred.

• Must be legally authorized to work in the United States and currently reside in the US.

• A quiet, professional home setup for video collaboration is required.

🏝️ Benefits

• Health, Dental, and Vision Insurance (including dependent coverage).

• Life & Disability Insurance.

• 20 vacation days.

• 10 sick days.

• 11 paid holidays in your first year.

• Retirement savings plan with up to 3% match of base salary.

• Flexible spending and dependent care accounts.

• Company-provided computer.

• Occasional travel to team retreats or important strategic meetings may be necessary.