Unsung Fields Corp.

Inference Systems Engineer | LLM Serving Runtime | English Only OK | Full Remote Available

AI Engineer

8M - ***M JPY

Kanagawa

Full-time (permanent)

Online Interview: Yes

Remote Work from Overseas: Yes / From Japan: Yes

Top-Selling Points

Rate of Foreigners

Less Than

Frequency of English Usage

Less Than

International employees Apply from overseas Remote work

Top-Selling Points

Rate of Foreigners
Less Than

Frequency of English Usage
Less Than

International employees Apply from overseas Remote work

Related Skills

Programming Language

Python C++

Language Requirements

Required

Preferred

Language Requirements

Required

Japanese: Daily Conversational

English: Business

Preferred

Japanese: Business

English: Daily Conversation

Job Description

[Recruitment Background]
With AI and machine learning set to become the foundation of society, the company aims to lead the world with next-generation AI cloud services. A strategic partnership with Tenstorrent, led by renowned semiconductor designer Jim Keller, marks the full-scale expansion into the global market. The mission extends beyond technical provision to driving client business success through innovation. The team seeks engineers to help transform cutting-edge AI chip technology into accessible infrastructure for everyone.

[Role overview]
As an inference & serving engineer, your objective is to build a high-performance, multi-tenant
serving stack that squeezes maximum utilization out of heterogeneous hardware. This involves
navigating the trade-offs between various state-of-the-art inference frameworks and engines,
selecting and optimizing the right runtime for the right workload. The scope of work is not limited
to Large Language Models; it extends to the frontier of Generative AI, including high-throughput
Video generation and complex Multimodal systems where memory pressure and compute
requirements are significantly more demanding.

Beyond just deploying models at scale, this role is responsible for building a robust system that
bridges the gap between boutique, high-performance clusters and massive, multi-node
deployments as the company grows. This requires a deep understanding of the "Inference
Triangle"—constantly tuning the stack to find the optimal equilibrium between low-latency
(TTFT/ITL), high-throughput, and inference quality (Precision/Quantization). The ideal candidate
is a hands-on engineer who views the entire GPU fleet as a single, programmable compute
fabric and is eager to get their hands dirty at every level of the stack.

[Responsibilities]
● Runtime Selection & Deep Optimization: Lead the evaluation, integration, and
continuous tuning of diverse inference frameworks to ensure best-in-class performance
across LLM, Video, and Multimodal workloads.
●Latency & Throughput Engineering: Own the end-to-end performance profile of the
model lifecycle, implementing advanced strategies such as disaggregated prefill/decode,
speculative decoding, and continuous batching to minimize TTFT and maximize tokensper-second.
●Scalable Systems Evolution: Design and implement serving architectures that function
seamlessly on small experimental clusters while providing a clear, robust path to
massive-scale, multi-node deployments.
●Advanced Memory & Cache Orchestration: Implement and optimize memory
management techniques to maximize KV-cache reuse and minimize redundant
computations in multi-turn or high-concurrency scenarios.
●Day 0 Model Support: Working with the ecosystem, craft a Day 0 model support
strategy ensuring our stack provides stable, high-performance support for new models
when they are released.
●Cross-Stack Integration: Collaborate with the Backend/Gateway and Compute
Orchestration teams to ensure the inference engine’s telemetry, failure domains, and
lifecycle management are perfectly aligned with the global load balancer and API layers.
●Hands-on Technical Leadership: Maintain a high level of personal agency by writing
production code, debugging complex distributed system "hangs," and contributing to
architectural decisions in a flat, fast-moving team environment.
●Collaborative Communication: Function as a primary technical peer to engineering
leads, translating complex hardware and model constraints into clear product and
infrastructure strategies.
●Inference Strategy & Trade-offs: Define path forward when balancing model precision
and quantization against the physical limits of HBM bandwidth and compute throughput.
● (Optional) Kernel-Level Development: Dive into the lowest levels of the execution
stack to develop and refine custom CUDA or Triton kernels, eliminating overhead in the
execution loop and optimizing for specific hardware primitives.

[You may be a fit if you have the following skills]
●Inference Engine: Deep experience with the internals of modern runtimes. You are a
prominent contributor to inference engine ecosystems, including but not limited to OSS
projects or proprietary engines at top-tier AI labs.
●Multimodal Domain Knowledge: Understanding of the specific challenges involved in
serving Large Language Models alongside Video and Vision-based generative models.
●Scale-First Engineering: A track record of building and managing distributed systems
that have evolved from small-scale proofs-of-concept to large-scale production
deployments
●Great Team Spirit: A mission-driven approach to engineering, valuing clear
communication, hands-on execution, and collective success over individual silos.
[Development Environment]
Primary Languages: Python, C++
Frameworks: LLM serving runtimes (e.g., vLLM family), distributed processing and inference runtime infrastructure
Database: Primarily in-memory (KV-cache management); time-series DB used for metrics
Cloud Services: Multi-accelerator environments (GPU/various Accelerators), hybrid cloud configurations
Others: Profiling and debugging tools, benchmarking infrastructure, observability tools (monitoring/dashboards), CI/CD, canary release infrastructure

[Impact and Achievements of Global Employees]
Foreign nationals from countries such as Sri Lanka, Uzbekistan, and Canada comprise half of the workforce. Both English and Japanese are used daily within the company.

[Work Environment]
Full remote work is available. Some employees work entirely remotely from locations outside of Japan.

Required Skills and Experiences

[Requirements] ● 5+ years building high-performance systems (model serving, GPU systems, performance engineering, or low-latency distributed systems). ● Strong understanding of LLM inference tradeoffs: batching vs latency, prefill vs decode dynamics, cache behavior, memory pressure, and tail latency causes. ● Comfort working across Python/C++ stacks with production profiling and debugging tools. ● Track record of shipping performance improvements that hold up under production variance and operational constraints. ● Strong engineering hygiene: tests, instrumentation, documentation, and careful rollout discipline. ● Ability to communicate clearly across teams and operate calmly during incidents.

After sign up, you can browse all information.

If you already have a GitTap Account, please login.

Working Condition

[Employment Type]
Permanent employee. Probation period: 3 months.

[Work Location]
*Full remote work is available. Some employees work remotely from locations outside of Japan.
■Address: 10F Queen's Tower A, 2-3-1 Minatomirai, Nishi-ku, Yokohama-shi, Kanagawa 220-6010
■Access:
7-minute walk from Sakuragicho Station (all lines).
Directly connected to Minatomirai Station (Minatomirai Line / Tokyu Toyoko Line).
■Smoking Policy: No smoking allowed on the premises (Entirely non-smoking).
■Scope of Change in Workplace: Any workplace designated by the company.
■Transfer/Secondment: None (No relocation or external secondment required).

[Expected Annual Salary]
Annual Salary: JPY 8,000,000 – 14,000,000
Monthly Salary: JPY 666,000 – 1,166,000
*Base Monthly Salary: JPY 666,000 – 1,166,000
■Salary Increase: Available (Based on performance review)

[Working Hours]
・Working Hours: 09:00 – 18:00
・Break Time: 60 minutes

[Benefits and Welfare]
Commuting Allowance: Partially covered (Up to JPY 15,000 per month). / Social Insurance: Fully covered (Health Insurance, Employee Pension, Employment Insurance, and Workers' Accident Compensation Insurance). / Overtime Pay: Paid according to actual overtime hours worked.

[Holidays and Leave]
Annual Holidays: 120 days / Five-day Workweek System / Annual Paid Leave: 10+ days (Starting from the 7th month of employment)

RECRUITMENT PROCESS

HR interview ⇒ departmental interview ⇒ technical interview ⇒ final interview ⇒ offer
*The number of times and content of the selection process (live coding, etc.) are subject to change depending on the situation.

Business (description what they do)

HPC Hosting AI Cloud System Development Business Process Optimization Automatic Solutions

Available Jobs in (Unsung Fields Corp.)

Recommended Jobs

NAP Co., Ltd.

【PL・PM】還元率120%/管理手当支給有

6M - ***M JPY | Tokyo(+3)

C C# C++

Japaniace Co., Ltd.

[SE / PG] TSE Growth Market Listed / Many Foreign Nationals / 133 Days Off

4.5M - ***M JPY | Hokkaido(+14)

Linux Unix Windows Server

ALiber Inc.

that allows you to develop freely in a stress-free environment such as human relationships ★

4M - ***M JPY | Tokyo(+9)

Java JavaScript Kotlin

Unsung Fields Corp.

Backend Engineer | English Only OK | Full Remote Available | Go, Python, Java

8M - ***M JPY | Kanagawa

Go Python Java

Top-Selling Points

Rate of Foreigners

Less Than

Frequency of English Usage

Less Than

International employees Apply from overseas Remote work

Top-Selling Points

Rate of Foreigners
Less Than

Frequency of English Usage
Less Than

International employees Apply from overseas Remote work

Related Skills

Programming Language

Python C++

Language Requirements

Required

Preferred

Language Requirements

Required

Japanese: Daily Conversational

English: Business

Preferred

Japanese: Business

English: Daily Conversation

Job Description

[Recruitment Background]
With AI and machine learning set to become the foundation of society, the company aims to lead the world with next-generation AI cloud services. A strategic partnership with Tenstorrent, led by renowned semiconductor designer Jim Keller, marks the full-scale expansion into the global market. The mission extends beyond technical provision to driving client business success through innovation. The team seeks engineers to help transform cutting-edge AI chip technology into accessible infrastructure for everyone.

[Role overview]
As an inference & serving engineer, your objective is to build a high-performance, multi-tenant
serving stack that squeezes maximum utilization out of heterogeneous hardware. This involves
navigating the trade-offs between various state-of-the-art inference frameworks and engines,
selecting and optimizing the right runtime for the right workload. The scope of work is not limited
to Large Language Models; it extends to the frontier of Generative AI, including high-throughput
Video generation and complex Multimodal systems where memory pressure and compute
requirements are significantly more demanding.

Beyond just deploying models at scale, this role is responsible for building a robust system that
bridges the gap between boutique, high-performance clusters and massive, multi-node
deployments as the company grows. This requires a deep understanding of the "Inference
Triangle"—constantly tuning the stack to find the optimal equilibrium between low-latency
(TTFT/ITL), high-throughput, and inference quality (Precision/Quantization). The ideal candidate
is a hands-on engineer who views the entire GPU fleet as a single, programmable compute
fabric and is eager to get their hands dirty at every level of the stack.

[Responsibilities]
● Runtime Selection & Deep Optimization: Lead the evaluation, integration, and
continuous tuning of diverse inference frameworks to ensure best-in-class performance
across LLM, Video, and Multimodal workloads.
●Latency & Throughput Engineering: Own the end-to-end performance profile of the
model lifecycle, implementing advanced strategies such as disaggregated prefill/decode,
speculative decoding, and continuous batching to minimize TTFT and maximize tokensper-second.
●Scalable Systems Evolution: Design and implement serving architectures that function
seamlessly on small experimental clusters while providing a clear, robust path to
massive-scale, multi-node deployments.
●Advanced Memory & Cache Orchestration: Implement and optimize memory
management techniques to maximize KV-cache reuse and minimize redundant
computations in multi-turn or high-concurrency scenarios.
●Day 0 Model Support: Working with the ecosystem, craft a Day 0 model support
strategy ensuring our stack provides stable, high-performance support for new models
when they are released.
●Cross-Stack Integration: Collaborate with the Backend/Gateway and Compute
Orchestration teams to ensure the inference engine’s telemetry, failure domains, and
lifecycle management are perfectly aligned with the global load balancer and API layers.
●Hands-on Technical Leadership: Maintain a high level of personal agency by writing
production code, debugging complex distributed system "hangs," and contributing to
architectural decisions in a flat, fast-moving team environment.
●Collaborative Communication: Function as a primary technical peer to engineering
leads, translating complex hardware and model constraints into clear product and
infrastructure strategies.
●Inference Strategy & Trade-offs: Define path forward when balancing model precision
and quantization against the physical limits of HBM bandwidth and compute throughput.
● (Optional) Kernel-Level Development: Dive into the lowest levels of the execution
stack to develop and refine custom CUDA or Triton kernels, eliminating overhead in the
execution loop and optimizing for specific hardware primitives.

[You may be a fit if you have the following skills]
●Inference Engine: Deep experience with the internals of modern runtimes. You are a
prominent contributor to inference engine ecosystems, including but not limited to OSS
projects or proprietary engines at top-tier AI labs.
●Multimodal Domain Knowledge: Understanding of the specific challenges involved in
serving Large Language Models alongside Video and Vision-based generative models.
●Scale-First Engineering: A track record of building and managing distributed systems
that have evolved from small-scale proofs-of-concept to large-scale production
deployments
●Great Team Spirit: A mission-driven approach to engineering, valuing clear
communication, hands-on execution, and collective success over individual silos.
[Development Environment]
Primary Languages: Python, C++
Frameworks: LLM serving runtimes (e.g., vLLM family), distributed processing and inference runtime infrastructure
Database: Primarily in-memory (KV-cache management); time-series DB used for metrics
Cloud Services: Multi-accelerator environments (GPU/various Accelerators), hybrid cloud configurations
Others: Profiling and debugging tools, benchmarking infrastructure, observability tools (monitoring/dashboards), CI/CD, canary release infrastructure

[Impact and Achievements of Global Employees]
Foreign nationals from countries such as Sri Lanka, Uzbekistan, and Canada comprise half of the workforce. Both English and Japanese are used daily within the company.

[Work Environment]
Full remote work is available. Some employees work entirely remotely from locations outside of Japan.

Required Skills and Experiences

After sign up, you can browse all information.

If you already have a GitTap Account, please login.

Working Condition

[Employment Type]
Permanent employee. Probation period: 3 months.

[Work Location]
*Full remote work is available. Some employees work remotely from locations outside of Japan.
■Address: 10F Queen's Tower A, 2-3-1 Minatomirai, Nishi-ku, Yokohama-shi, Kanagawa 220-6010
■Access:
7-minute walk from Sakuragicho Station (all lines).
Directly connected to Minatomirai Station (Minatomirai Line / Tokyu Toyoko Line).
■Smoking Policy: No smoking allowed on the premises (Entirely non-smoking).
■Scope of Change in Workplace: Any workplace designated by the company.
■Transfer/Secondment: None (No relocation or external secondment required).

[Expected Annual Salary]
Annual Salary: JPY 8,000,000 – 14,000,000
Monthly Salary: JPY 666,000 – 1,166,000
*Base Monthly Salary: JPY 666,000 – 1,166,000
■Salary Increase: Available (Based on performance review)

[Working Hours]
・Working Hours: 09:00 – 18:00
・Break Time: 60 minutes

[Benefits and Welfare]
Commuting Allowance: Partially covered (Up to JPY 15,000 per month). / Social Insurance: Fully covered (Health Insurance, Employee Pension, Employment Insurance, and Workers' Accident Compensation Insurance). / Overtime Pay: Paid according to actual overtime hours worked.

[Holidays and Leave]
Annual Holidays: 120 days / Five-day Workweek System / Annual Paid Leave: 10+ days (Starting from the 7th month of employment)

RECRUITMENT PROCESS

HR interview ⇒ departmental interview ⇒ technical interview ⇒ final interview ⇒ offer
*The number of times and content of the selection process (live coding, etc.) are subject to change depending on the situation.

Business (description what they do)

HPC Hosting AI Cloud System Development Business Process Optimization Automatic Solutions

Available Jobs in (Unsung Fields Corp.)

Recommended Jobs

ALiber Inc.

that allows you to develop freely in a stress-free environment such as human relationships ★

4M - ***M JPY | Tokyo(+9)

Java JavaScript Kotlin

kknexes

[IT Engineer] Remote available/ Visa support/Java, PHP, Perl, C#, and many other projects available.

5M - ***M JPY | Tokyo(+5)

Java PHP Perl

Unsung Fields Corp.

Backend Engineer | English Only OK | Full Remote Available | Go, Python, Java

8M - ***M JPY | Kanagawa

Go Python Java

NAP Co., Ltd.

【SE】◆フリーランス採用◆常時１万件以上の案件

5M - ***M JPY | Tokyo(+3)

.NET C C#