> Markdown version of [/jobs/ext/4199583-ai-engineer](https://www.wearedevelopers.com/jobs/ext/4199583-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# AI Engineer

- **Company:** MOGEL RPO LLC
- **Location:** Boston, MA, United States
- **Salary:** $129,339.0 - $200,000.0
- **Contract:** Permanent contract
- **Skills:** LangGraph Framework, AI Evaluation, Application Programming Interfaces (APIs), Artificial Intelligence, Software Applications, Automated Storage and Retrieval Systems, Automation of Tests, Information Leak Prevention, Software Debugging, Python (Programming Language), Key Management, Machine Learning, Cloud Services, Software Engineering, TypeScript, Large Language Models, Model Validation, Agentic-AI, Information Technology, Data Analytics, OpenClaw (Open-source Robotic Gripper), Asynchronous Programming
- **Published:** October 30, 2026
- **Apply:** https://www.careerjet.com/job/us2a567e499043cdbcbd42215481e0828c/eaa

## About the Role

Bachelor's degree in Computer Science, Engineering, or a related field, with at least five years of software engineering or machine learning engineering experience, or an equivalent combination of education and experience.
Hands-on experience developing LLM-powered applications involving tool use, retrieval, structured outputs, and systematic evaluation.
Ability to analyze AI system failures, explain performance limitations, and demonstrate improvements through testing and evaluation.
Strong proficiency in Python or TypeScript, including experience with APIs, asynchronous programming, data models, testing, cloud services, and debugging across system boundaries.
Practical understanding of sandboxing, system isolation, access controls, secrets management, and security risks associated with agentic AI systems.
Strong analytical and problem-solving skills, with the ability to conduct structured experiments and make data-driven technical decisions.
Ability to work effectively in a collaborative, fast-paced environment where requirements and technical approaches may evolve.
Strong communication skills and the ability to document technical findings, explain trade-offs, and collaborate across disciplines.
Preferred Qualifications
Experience developing multimodal or voice-based AI applications.
Familiarity with agent orchestration, model adaptation, or AI evaluation infrastructure.
Demonstrated interest in experimenting with emerging AI models, tools, and development techniques.
Experience with agentic AI frameworks or toolkits such as LangChain, LangGraph, Deep Agents, OpenClaw, Hermes, or comparable technologies.
Experience designing evaluation and monitoring processes for AI systems operating in dynamic or production-like environments.

## Description

MOGEL RPO is partnering with an innovative edtech organization and is seeking an AI Engineer to help develop and evaluate innovative AI-powered applications and intelligent agent systems.
This hands-on role focuses on experimenting with emerging AI technologies, building prototypes, and transforming promising concepts into reliable, secure software. You will work with large language models (LLMs), agentic workflows, retrieval systems, and model evaluation techniques to develop practical AI solutions.
The ideal candidate is an inventive engineer who enjoys exploring new approaches, solving complex technical challenges, and collaborating with product, research, and engineering teams. Success in this role requires strong technical skills, disciplined experimentation, and the ability to evaluate results, identify limitations, and continuously improve AI system performance., Prototype AI applications and agentic workflows using model APIs, tool calling, retrieval-augmented generation (RAG), structured outputs, and state management.
Evaluate and compare AI models and architectures for different use cases, applying fine-tuning or other model adaptation techniques when supported by evaluation results.
Develop evaluation datasets, automated testing processes, and human review workflows to measure quality, reliability, robustness, and regression risks.
Analyze model traces, errors, and failure patterns to improve grounding, tool reliability, context management, and recovery from unexpected outputs.
Design secure, sandboxed execution environments for AI agents and generated code, incorporating least-privilege access, network and filesystem restrictions, secrets protection, and resource limits.
Test for prompt injection, data leakage, and unintended actions, implementing output validation, isolation boundaries, and auditable execution practices in collaboration with security teams.
Measure and optimize latency, throughput, inference costs, and overall system performance.
Collaborate with application engineers, product teams, and research specialists to develop observable, testable, and maintainable AI software.
Explore emerging AI techniques, document findings and limitations, and recommend which approaches to pursue, refine, or discontinue.
Perform additional duties and support AI engineering initiatives as needed.