Agent Harness Engineer (KP)

 

【JAPAN AI】Agent Harness Engineer / English

 

雇用形態 正社員

給与 年収 9,000,000 円 - 16,000,000円

Monthly: ¥857,143～¥1,428,571 (incl. 45h fixed overtime)

Stock options available

Reviews & bonuses: twice/year

OT beyond 45h paid separately

Negotiable based on experience and skills

勤務地 東京都新宿区西新宿住友不動産新宿オークタワー ５/６階

Work Style Hybrid work : 3 days in office, 2 days remote

Flexible working hours : Core time is negotiable

Flexibility : Future consideration for more flexible work styles is

possible

Hiring Process 1. Application Review

2. Coding Assessment

3. Interviews (4–5 rounds)

4. Offer

Mission

"Design the heart of 'the brain of the enterprise.'"

Design and implement the Agent Harness — execution engine, orchestration, guardrails,

memory, and model routing — that enables AI agents to operate safely, quickly, and reliably.

 

 

Build the control foundation for hundreds of workflows running on JAPAN AI STUDIO, entirely

in-house.

What Is an Agent Harness?

An Agent Harness is the control and execution infrastructure layer that wraps AI models. While

Agent Frameworks (e.g., LangChain) handle agent construction , the Agent Harness handles

agent control and operation .

Backend Engineer

What you build : Web APIs, microservices

Relationship with AI/ML : Calls ML models via API

State management : Stateless request/response

Safety controls : Authentication, authorization, input validation

/////

Agent Harness Engineer

What you build : LLM-centric agent execution engines, SDKs, orchestrators

Relationship with AI/ML : Designs model routing, RAG integration, context injection, and

inference optimization at the system level

State management : Agent session management, checkpoints, long-term memory, working

memory

Safety controls : Guardrail/policy execution engine — a rule execution layer that controls LLM

output

 

 

 

 

 

● At the intersection of AI/ML × Backend — Design and implement the agent

execution infrastructure with deep understanding of LLM operating principles.

Neither pure infrastructure nor pure ML — a new domain.

● Foundation software designer — This is not a job writing YAML. You will build

SDKs, execution engines, and orchestrators in code. Low-level knowledge directly

applies.

● Developer experience architect — Design the SDK and toolchain used by 120

in-house engineers, improving productivity across the entire development

organization.

● Powering every product — In a production environment used by ~200

companies, every AI agent runs on the Harness you build.

● Rapid-growth environment — In a startup that has grown to 200+ people and 9

products in just 3 years, you will have significant autonomy in technical

decision-making.

Job Description

● Agent Harness design & implementation

○ Design and implement the agent execution engine (Graph Runtime /

State Machine)

○ Design and develop the Agent SDK — the interface for in-house

engineers to build agents

○ Implement session management, checkpoint, and recovery mechanisms

○ Build the guardrail / policy execution engine — a rule execution

infrastructure that controls agent behavior

● AI/ML System Integration

○ Model routing — optimal routing of inference requests across multiple

LLM providers and model types

○ Design context management and memory infrastructure (long-term

memory, working memory, RAG integration)

 

 

○ Optimize inference pipelines (latency reduction, cost efficiency, caching

strategies)

○ Integrate latest research findings into the production infrastructure in

collaboration with Research Engineers

● Orchestration & performance

○ Develop workflow orchestration and queuing systems

○ Cost/performance optimization (autoscaling, caching, batch processing)

○ Inference request routing and load balancing

● Reliability & Operations

○ Maintain platform uptime of ≥99.9%

○ Incident response and post-mortems

○ Design data access and permission management infrastructure

Key Results (KRs / Metrics)

● Agent SDK adoption rate (in-house team usage rate and satisfaction)

● Agent execution success rate (task completion rate, checkpoint recovery success

rate)

● Harness-attributed failure rate (guardrail breach rate, state inconsistency rate)

● Execution latency P95 / P99 (Harness layer overhead)

● Inference cost efficiency (cost optimization through model routing)

● Developer experience score (internal NPS for SDK / API)

Team Structure

Approximately 120 members are part of the development organization.

● Agent Harness Engineers work across the following groups:

○ Infra — Cloud infrastructure and SRE

 

 

○ Data — Data pipelines and analytics infrastructure

○ Agent Harness — Agent execution framework

● Closely collaborating roles:

○ Agentic Product Engineer — Agent feature development (SDK users)

○ Research Engineer — R&D and integration of new methods into the

infrastructure

○ AI QA Specialist — Evaluation pipeline collaboration

○ Product Manager — Product design and non-functional requirements

definition

You May Be a Good Fit If You

● Bachelor's degree or equivalent practical experience in Computer Science,

Software Engineering, Artificial Intelligence, Machine Learning, Mathematics,

Physics, or related fields

● 5+ years of practical experience as a backend engineer

● Production product development experience in Python

● Experience designing and implementing production systems that leverage LLM / AI

agents

● Experience designing and implementing distributed systems (including design and

coding, not just operations)

● Experience designing and implementing RESTful APIs / gRPC

● Language requirement (at least one of the following):

○ Japanese: Fluent — able to discuss product development without friction

○ English: Business level

Strong Candidates May Also Have

 

 

● Agent Framework / Agent Harness design and implementation experience

(LangChain / LangGraph / AutoGen, etc.)

● Production operations experience on cloud platforms (AWS / GCP / Azure)

● Understanding of RAG systems, vector databases, and memory architectures

● Model routing and inference optimization experience

● Foundation software development experience in Go (SDKs, runtimes, frameworks,

etc.)

● Deep understanding of Kubernetes / container orchestration

● Event-driven architecture experience (Kafka / RabbitMQ, etc.)

● Experience implementing safety guardrails, policy execution, and AI observability

● ML infrastructure / MLOps construction experience

● Technical communication ability in English

Tech Stack

● Languages : Python, Go (backend / infrastructure), TypeScript / React / Next.js

(frontend), NX

● Infrastructure : GCP (containers / K8s), Docker, Terraform

● Messaging : Kafka, Pub/Sub

● Monitoring : Prometheus, Grafana, OpenTelemetry

● Tools : Slack, Confluence, Linear, Google Workspace, GitHub, Notion

● AI Dev Support: Claude Code MAX Plan, Cursor, ChatGPT, Devin

● Workstation : Mac (Apple Silicon), dual monitor setup

Learning & Development Support

 

 

● AI Tool Usage Support

○ Company covers the cost of using AI tools such as JAPAN AI SaaS

services, Cursor, ChatGPT, Claude, etc.

● Development Tool Support

○ If a desired development tool is paid, the cost is covered (up to ¥30,000

per year)

● Book Purchase Assistance

○ Company covers the cost of purchasing books for learning, such as

technical books (up to ¥30,000 per half-year)

● Language Learning / Qualification Support

○ Company covers the cost of Japanese or English learning programs and

qualification acquisition

● Refresh Allowance

○ Company covers the cost of services used for personal refreshment (up

to ¥5,000 per month)

○ e.g., gym, yoga, chiropractic, aquarium, movies, theme park tickets, etc.

● Housing Allowance

○ Housing allowance provided for those living in designated areas (up to

¥30,000 per month)