AI/ML Engineer – LLM & AI Harness Engineering

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

📋 Description

• Design and validate AI/ML and LLM workflows utilizing Python for engineering analyses, technical data processing, automation, and decision-making support.

• Construct model training and validation pipelines leveraging open datasets along with engineering datasets, including s-parameters, VNA, simulation, test, and measurement data.

• Employ machine learning and deep learning methodologies, such as neural networks, CNNs, and LSTM/recurrent models, to tackle engineering challenges.

• Create LLM workflows for tasks like data parsing, summarization, extraction, classification, and generating structured outputs.

• Architect and implement RAG solutions based on reliable engineering documents, datasets, and sanctioned knowledge sources.

• Develop AI-agent and LLM harness workflows that incorporate task routing, tool invocation, workflow orchestration, evaluation, and safety measures.

• Create or integrate bespoke tools for AI engagement with engineering and technical data sources.

• Work in collaboration with signal integrity, product development, testing, manufacturing, and operations teams on AI automation and decision-making support.

• Convert technical requirements into dependable, reusable AI workflows and prototypes.

• Document workflows, assumptions, validation methods, limitations, and suggested next steps.

• Assess AI-generated results, identify associated risks and limitations, and propose enhancements.

⛳️ Requirements

• A bachelor's degree in Engineering, Computer Science, Data Science, Applied Mathematics, or a closely related technical field; a master's degree is advantageous.

• Proficient hands-on experience with Python for AI/ML development, data processing, model training, validation, and automation.

• Solid understanding of machine learning and deep learning concepts, including neural networks, CNNs, and LSTM/recurrent architectures.

• Familiarity with PyTorch, TensorFlow, or similar AI/ML frameworks.

• Knowledge of GPU-accelerated AI/ML development and CUDA, especially within NVIDIA environments.

• Practical experience with Large Language Models and familiarity with both open-source and/or commercial AI models.

• Experience with tools such as Ollama, LM Studio, llama.cpp, or similar local LLM/model-serving technologies.

• Experience with frameworks such as Hugging Face, LangChain, or comparable AI/LLM platforms.

• Strong understanding and practical application of Retrieval-Augmented Generation (RAG).

• Capability to design AI-agent/harness architectures that integrate RAG, tool invocation, workflow orchestration, evaluation, safety measures, and external data sources.

• Excellent analytical and problem-solving skills with a focus on validating AI outputs and comprehending model limitations.

• Strong communication skills, with the ability to convey AI concepts and technical trade-offs to engineering stakeholders effectively.

• Ability to work autonomously, learn swiftly, and collaborate within a global technical organization.

• Nice-to-have: experience with engineering, signal integrity, measurement, simulation, test, product development datasets, AWS AI/data environments, Jupyter notebooks, LLM fine-tuning, model serving, GPU optimization, and related engineering settings.

🏝️ Benefits

• Opportunity to work on cutting-edge AI and ML projects.

• Collaborative and innovative work environment.

• Professional development and growth opportunities.

• Competitive salary and benefits package.