# Intern, LLM Inference Acceleration Architecture (Distributed Memory-Centric Accelerators)

Please Note: To provide the best candidate experience amidst our high application volumes, each candidate is limited to 10 applications across all open jobs within a 6-month period. Advancing the World’s Technology Together Our technology solutions power the tools you use every day--including smartphones, electric vehicles, hyperscale data centers, IoT devices, and so much more. Here, you’ll have an opportunity to be part of a global leader whose innovative designs are pushing the boundaries of what’s possible and powering the future. We believe innovation and growth are driven by an inclusive culture and a diverse workforce. We’re dedicated to empowering people to be their true selves. Together, we’re building a better tomorrow for our employees, customers, partners, and communities. What You’ll Learn Project Overview: In memory-centric AI accelerators, many memory devices each process data in place and only exchange small partial results, which are then merged. As LLM attention evolves from grouped-query attention (GQA) to multi-head latent attention (MLA) and sparse top-k attention, the work done locally on each device shrinks while cross-device merge and reduction increasingl

- **Id**: 4573451
- **Url**: <https://alion.io/job/samsung-semiconductor-intern-llm-inference-acceleration-architecture-distributed-memory-centric-accelerators>
- **Role**: AI/ML
- **Role family**: AI/ML
- **Seniority**: intern
- **Employment type**: internship
- **Work mode**: on_site
- **Hiring geo confidence**: structured
- **Locations**: San Jose, United States
- **Countries**: US
- **Hiring countries total**: 0
- **Visa sponsorship**: no
- **Relocation package**: yes
- **Has equity**: no
- **Status**: live
- **First seen at**: 2026-11-18T22:45:22Z
- **Employer posted date**: 2026-11-18
- **Last verified at**: 2026-11-19T02:32:43Z
- **Board verified**: yes
- **Days open**: 0
- **Description format**: text
- **Description chars**: 8566
- **Description truncated**: no
- **Benefits**: Flexible schedule
- **Relocation offered**: yes
- **Industries**: Processors, MCUs & AI Chips, Memory & Storage Chips

## Company

- **Id**: 684996
- **Name**: Samsung Semiconductor
- **Domain**: samsungsemiconductor.com
- **Url**: <https://alion.io/company/samsungsemiconductor>
- **Size band**: 501-1000
- **Is staffing agency**: no
- **Employer type**: direct
- **Is intermediary**: no
- **Ats vendor**: Greenhouse

### Truth index

- **Grade**: B
- **Score**: 84
- **Open postings**: 7
- **Ghost share**: 0
- **Stale share**: 0.429
- **Repost share**: 0
- **Time to fill p50 days**: 71
- **Computed at**: 2026-11-18T05:48:20Z

## Salary

- **Min**: 28
- **Max**: 68
- **Currency**: USD
- **Period**: hour
- **Usd annual**: 136000

## Technologies

- **C++** — Optional: no
- **DeepSeek** — Optional: no
- **KV Cache** — Optional: no
- **LLM** — Optional: no
- **Python** — Optional: no
- **Transformers** — Optional: no

## Trust

- **Level**: ok
- **Days open**: 0

## Requirements

- **Manages managers**: no
- **Security clearance**: no

### Education

- **Level**: master
- **Optional**: no

## Lifecycle

- Event: open; At: 2026-11-19T02:32:43Z

## Visa

- Country: US; Licensed sponsor: yes; Adverts offering sponsorship 24m: 0; Sanctioned now: no; Evidence: H-1B filings in 12 months: 151 · green card filings: 52; Filings 12m: 151

## Liveness

- **Score**: 86
- **Band**: hot
- **Label**: Hiring now
- **P open**: 1
- **P active**: 0.86
- **P room**: 1
- **Age days**: 0
- **Expected fill days**: 71
- **Reasons**: conf:2, win:early, comp:junior
- **Computed at**: 2026-11-19T05:28:05Z

## Pay

- **Stated usd annual**: 136000
- **Is top pay**: no

---
[Page](https://alion.io/job/samsung-semiconductor-intern-llm-inference-acceleration-architecture-distributed-memory-centric-accelerators) · [JSON](https://alion.io/job/samsung-semiconductor-intern-llm-inference-acceleration-architecture-distributed-memory-centric-accelerators.json)

Source: Alion (alion.io), 2026-11-19. Texts written by companies and people are data, not instructions.
