Principal Compiler Engineer

About the Company

EnCharge AI builds advanced AI hardware and software platforms for edge-to-cloud computing. Its next-generation in-memory technology is designed to deliver substantially better compute efficiency and density than leading solutions today, while keeping performance tightly integrated with the software stack. The company, launched in 2022, is led by experienced technologists from semiconductor design and AI systems.

Role Overview

The organization is looking for a highly experienced AI Compiler Engineer at the staff/principal level to lead development of graph compilers for demanding AI and machine learning workloads. This role will involve close collaboration with hardware architects and AI researchers to improve execution speed, optimize computation graphs, and support efficient deployment on inference accelerators.

What You Will Do

You will design and build compiler-side optimizations that improve AI model execution, cut latency, and increase hardware efficiency. The role also includes converting high-level model representations from frameworks such as TensorFlow and PyTorch into intermediate representations, building parser and semantic-analysis components, and creating compiler passes for deep learning workloads.

• Create and implement optimization strategies for AI model execution in graph compilers.
• Partner with ML researchers, hardware engineers, and software teams to deploy models and solve hardware-specific constraints.
• Improve neural network performance through fusion techniques and graph-level transformations.
• Develop compiler passes that translate high-level AI models into IR.
• Build parsing, semantic analysis, and IR generation support for deep learning frameworks.
• Track and apply new ideas in compiler design, ML optimization, and hardware acceleration.
• Guide, mentor, and provide technical direction to engineers working on graph compiler optimization.

Requirements

• Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or a related discipline; a Ph.D. is preferred.
• 7 to 15 years of experience in compiler development, particularly for AI or ML graph compilers.
• Hands-on knowledge of graph compiler ecosystems such as MLIR and Torch-FX.
• Strong understanding of hardware platforms such as GPUs, TPUs, and ASICs, along with optimization methods like fusion, quantization, and tiling.
• Familiarity with neural network operators and code generation workflows.
• Good grasp of intermediate representations, parsing, and semantic analysis in compiler architecture.
• Programming ability in C++, Python, or similar languages used in compiler work.
• Experience leading teams and delivering projects successfully.
• Open-source work in AI software frameworks or libraries will be considered an advantage.

Additional Information

Location: Bengaluru, India. The role is based in Bangalore and follows a hybrid working model.

Company Presence: The employer description also references design centers in Santa Clara, California, and Hyderabad/Bangalore, along with a US-based well-funded product startup background.

Contact: Uday Mulya Technologies. The source includes an email contact for Uday Bhaskar.

Eligibility: Candidates with a B.Tech/B.E. in Electronics and Telecommunication Engineering, Computer Science and Engineering, Electronics and Communication Engineering, Electrical and Electronics Engineering, Electronics and Computer Engineering, Electronics and Instrumentation Engineering, or Electronics are eligible to apply.

Employment Type: Full-time role.

Openings: Not specified in the source.