AI/CAD Software Engineer

Falcomm•Atlanta, GA

14h

About The Position

Are you passionate about applying machine learning to transform the future of RF hardware? At Falcomm, we are revolutionizing wireless communications by integrating AI-driven solutions into the design of our energy-efficient Power Amplifier (PA) products. We are seeking a full-time AI/CAD Software Engineer to join our team. You will lead the development of intelligent tools that enhance RF workflows, automate complex EM simulations, and accelerate the tape-out of high-performance PAs. This role sits at the intersection of software engineering, machine learning, and RF physics, perfect for a developer who wants to get close to the hardware.

Requirements

Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or a related field.
2+ years of professional experience in software engineering or machine learning.
Proficiency in Python: Advanced scripting, object-oriented programming, and automation skills.
ML Framework Expertise: Experience building models using PyTorch, TensorFlow, or scikit-learn.
Data Engineering: Strong grasp of data processing libraries (pandas, numpy, scipy) and file I/O operations.
Software Fundamentals: Solid understanding of algorithms, data structures, and version control (Git).

Nice To Haves

RF & PA Domain Knowledge: Experience with Power Amplifier design, RF front-end architectures, or a strong understanding of RF metrics (PAE, Gain, ACLR, EVM).
RF/EM Simulation Tools: Hands-on experience with Cadence Virtuoso, Ansys HFSS, or Keysight ADS.
Open Source Innovation: Experience utilizing or contributing to open- source RF/EDA alternatives (e.g., gdsfactory, KLayout, Qucs, openEMS).
Simulation Scripting: Familiarity with automating RF simulations via SKILL, AEL, or Python APIs.
Physics-Informed ML: Interest or experience in applying ML to physics- based problems or electromagnetic modeling.

Responsibilities

End-to-End ML Pipeline Development: Architect and maintain robust code for training and serving ML models that predict and optimize RF performance metrics.
PA Design Automation: Automate the creation and management of large-scale datasets derived from PA load-pull and electromagnetic (EM) simulations.
Tool Integration: Seamlessly integrate ML inference engines into existing RF EDA infrastructure to provide real-time feedback to PA designers.
Software Engineering Excellence: Establish best practices including comprehensive testing, CI/CD pipelines, and code reviews within an agile hardware team.
Cross-Functional Collaboration: Partner closely with RF/PA architects to translate complex impedance matching and linearity requirements into deployable software solutions.