AI Engineer

Sourced from edtech.com

• Prototype AI applications and agentic workflows using model APIs, tool calling, retrieval, structured outputs, and state management
• Compare models and architectures per use case; apply fine-tuning or model adaptation when evaluation shows an advantage
• Build evaluation datasets, automated checks, and human review workflows to measure quality, robustness, and regressions
• Diagnose failures via traces and error analysis; improve grounding, tool reliability, and context handling
• Design sandboxed execution with least-privilege access, network/filesystem restrictions, and secrets protection
• Test for prompt injection, data leakage, and unintended actions; implement output validation and isolation boundaries
• Measure latency, throughput, and inference costs; collaborate with application engineers and learning researchers
• Test emerging techniques, document findings, and help the team decide what to pursue, revise, or stop

• Bachelor's degree in computer science, engineering, or a related field and 5+ years of software or machine learning engineering experience, or equivalent combination of education and experience
• Hands-on experience building LLM applications with tool use, retrieval, structured outputs, and evaluation
• Strong Python or TypeScript skills with APIs, asynchronous code, data models, testing, and cloud services
• Practical understanding of sandboxing, isolation, access controls, secrets management, and security risks in agentic systems
• Must reside in the Boston, MA area

• Experience with multimodal or voice AI
• Agent orchestration and model adaptation experience
• Evaluation infrastructure experience
• Active experimentation with emerging AI methods
• Familiarity with agentic toolkits such as Deep Agents, LangChain, LangGraph, OpenClaw, or Hermes