About the Role
As our Principal AI Model Architect, you will shape the hardware around the model before a single transistor is placed. You are the living contract between what our researchers dream up and what our silicon team can physically build. This role involves deep, architecture-level surgery—partitioning massive parameter models, defining tiling strategies, and projecting cycle-accurate performance on silicon that doesn't exist yet.
Responsibilities
- Own the translation layer by converting bleeding-edge AI and RAN algorithms into precise hardware specifications for the ASIC team and concrete lowering requirements for the SDK team.
- Define strategies for decomposing and mapping massive, multi-hundred-million parameter models across heterogeneous compute fabrics, including tensor parallelism, pipeline stages, and tiling across HBM and on-chip SRAM.
- Own and maintain canonical reference implementations in JAX and PyTorch as the Source of Truth for the entire program.
- Project performance using cycle-accurate simulators, SystemC models, and intuition to give the silicon team confidence in multi-million dollar tape-out decisions.
Requirements
- Deep, battle-tested knowledge of Transformer architectures, including how design choices impact hardware execution profiles.
- Experience in Hardware-Aware ML, considering cache line behavior, memory wall bottlenecks, and how SIMD and VLIW execution units reward specific model shapes.
- Advanced proficiency in JAX (preferred), PyTorch, or TensorFlow, specifically at the export and compilation layer, including graph capture, XLA compilation, and StableHLO representations.
- Experience with SystemC, Transaction-Level Modeling, or custom cycle-accurate simulation frameworks to validate architectural decisions.
- Experience applying AI to real RAN workloads (e.g., channel estimation, beamforming, interference management at L1/L2/L3).
- Instinctive understanding of the journey from a high-level compute graph to a linearized, scheduled, hardware-bound execution sequence.
- Hands-on experience with complex-valued AI models and their mapping to DSP and matrix accelerator hardware, including fixed-point quantization, dynamic range, and numerical stability under precision reduction.
Skills
- Transformer architectures
- Hardware-Aware ML
- JAX
- PyTorch
- TensorFlow
- SystemC
- Transaction-Level Modeling
- Cycle-accurate simulation
- RAN workloads
- MLIR
- Complex-valued AI models
- Fixed-point quantization
Location
- Austin, Texas
Work Type
- Full-time
Experience Level
- Principal
Salary/Compensations
- The salary range for this position is dependent on various factors including, but not limited to, location, and the candidate’s combination of job-related knowledge, qualifications, skills, education, training, and experience.
Benefits
- Choice of three medical plan options
- Dental plan option
- Company credits towards medical and dental premiums
- 401(k) Plan with automatic 3% company contribution
- 401(k) Plan with company match $1 for $1 on the first 3% of eligible pay, plus 50 cents on every $1 on the next 2% of eligible pay
- Company credits for basic life insurance and basic accidental death and dismemberment coverage
- Company credits for short-term and long-term disability coverage
- Option to participate in Stock Purchase Plan
- 15 days of accrued vacation
- Up to 3 personal days per year
- 11 annual holidays
- 8 hours of volunteer time
- 80 hours of sick time annually
- Up to 16 weeks of paid maternity leave
- 6 weeks of parental or adoption leave at 100% of pay
- Financial wellness programs
- Educational assistance
- Matching gifts
- Recognition programs
About the Company
- Ericsson uses a merit-based hiring approach that values people with different experiences, perspectives and skillsets.
- Ericsson truly believes this approach drives innovation, which is essential for our future growth.
Equal Opportunity
- Ericsson is proud to be an Equal Opportunity employer, learn more.
- If you need assistance or to request an accommodation due to a disability, please contact Ericsson at hr.direct.americas@ericsson.com.
