T

Texas Instruments

Makes analog and embedded chips in its own plants

Compute In-Memory System Engineer Intern

Silicon & ASIC DesignPosted on Nov 19
Internship · Summer 2026Dallas, TX, USANo salary listedIn-person

About the Job

Requirements

  • Currently pursuing a PhD in Electrical Engineering, Computer Engineering, Electrical and Computer Engineering, or a related field.
  • Have a cumulative GPA of 3.0/4.0 or higher.

Responsibilities

  • Research and develop novel digital compute-in-memory architectures optimized for edge AI workloads on resource-constrained microcontrollers.
  • Explore tiling digital compute-in-memory macros and combining multiple tiles to scale compute throughput within area, power, and cost budgets.
  • Study inter-tile architecture trade-offs, including dataflow, workload partitioning and mapping across tiles, tile-to-tile communication, scheduling, and utilization.
  • Quantify throughput, energy efficiency (TOPS/W), and area scaling of tiled compute-in-memory versus conventional NPU/MAC-array approaches, including mixed-precision and sub-8-bit quantization impacts.
  • Explore algorithm-hardware co-design techniques to maximize energy efficiency and computational throughput.
  • Collaborate with internal technology and design teams to simulate and validate compute-in-memory-based solutions.
  • Develop and optimize machine learning models and inference flows tailored for in-memory computing paradigms.
  • Participate in designing and implementing software toolchains and simulation frameworks for compute-in-memory and tiled-compute-in-memory evaluation.
  • Investigate memory hierarchy optimizations and data movement reduction strategies for edge processing.
  • Document findings and present trade-offs and recommendations to architecture, design, and business stakeholders.

Desired Qualifications

  • Have a solid background in computer architecture, digital design, memory systems, and/or embedded systems.
  • Have research experience in compute-in-memory, processing-in-memory, or near-memory computing, ideally demonstrated by publications at leading architecture, circuits, or systems venues such as ISCA, MICRO, HPCA, DAC, or ISSCC.
  • Be familiar with scalable or multi-tile accelerator architectures, including dataflow, mapping, and scheduling of neural networks across multiple compute tiles.
  • Be proficient in hardware description languages such as Verilog or VHDL and/or architectural simulation tools.
  • Have strong programming skills in Python and C/C++, including performance analysis and optimization.
  • Have experience with machine learning model optimization, quantization including sub-8-bit quantization, and deployment on resource-constrained devices.
  • Have knowledge of SRAM/DRAM circuit design and memory architecture principles.
  • Be familiar with deep learning frameworks such as PyTorch and TensorFlow, and embedded machine learning libraries such as TensorFlow Lite and CMSIS-NN.
  • Understand energy-efficient computing techniques and power/area modeling.
  • Have experience with algorithm-hardware co-design methodologies.
  • Be able to establish strong relationships with internal and external stakeholders critical to success.
  • Have strong verbal and written communication skills for audiences of varied backgrounds.
  • Be able to simplify complex problems and navigate uncertainty.
  • Be able to quickly ramp up on new systems and processes.
  • Demonstrate strong interpersonal, analytical, and problem-solving skills.
  • Be able to work in teams and collaborate effectively with people in different functions.
  • Be able to take initiative and drive for results.
  • Have strong time-management skills to enable on-time project delivery.

About the Company

Texas Instruments

Makes analog and embedded chips in its own plants

Texas Instruments designs and makes analog and embedded processing chips, the basic parts inside cars, factory equipment, data centers, and consumer electronics, and it sells one of the broadest chip catalogs in the industry. In 1958, its engineer Jack Kilby built the first integrated circuit, the building block of modern electronics, and later won a Nobel Prize for it. Its analog chips regulate power and convert signals such as sound and heat into data, while its microcontrollers act as small built-in computers, and TI earns money selling both to device makers. It also makes the graphing calculators many students use in math class. Texas Instruments was founded in 1930 and is based in Dallas, Texas.

Company size
10,001+
Company stage
IPO
Headquarters
Dallas, TX
Founded
1930

Recently Posted Jobs

Explore more opportunities at Texas Instruments

See more jobs