핵심 요구사항
- 8년 이상 프로덕션 엔터프라이즈 시스템 개발 경험
- 데이터 집약적 복잡한 React 인터페이스 구축 경험
- 멀티테넌트·분산 백엔드 및 필수 인증/인가 경험
- PostgreSQL 스키마 설계·마이그레이션·쿼리 성능 최적화
- 워크플로우 엔진·큐·이벤트 기반 등 비동기/내구성 시스템 경험
- UI~DB~워커~외부연동 전반 프로덕션 디버깅 능력
Required stack
필요 기술
ReactNestJSPostgreSQLTemporal.ioNode.jsTypeScriptLLM APIVite
Project brief
프로젝트 내용
Headquarters: United Kingdom
URL: https://www.aguru.ai/
Senior Full Stack Engineer
Location: Remote, EU/UK preferred
Team: Engineering
Type: Full-time contractor
We are looking for a Senior Full Stack Engineer to join a small, high-impact engineering team. You will work across the product surface: React front end, NestJS backend, durable execution system, Postgres data layer and proprietary systems for evaluating and managing systems of LLMs. Some of this you may not have done before, but you will apply your transferable skills and experience!
This role suits someone who enjoys a variety of challenges, extending the forefront of what it takes to deliver reliable and trustworthy AI systems, and making those things simple and a joy to use. You will understand product needs, design clean domain models, build reliable components, ship easy-to-use interfaces, and debug distributed execution behaviour when things get interesting.
What You’ll Work On
-
Build product features across our React/Vite frontend, NestJS backend, PostgreSQL data layer, and Temporal-powered worker stack.
-
Develop new ways to benchmark and optimise LLM use, including error detection and correction and blocking AI-focused security attacks
-
Identify where AI can meaningfully improve structured tasks (and not make things worse): extraction, classification, decision support, agentic tool use, document understanding, communication handling, and automation of tedious operational steps.
-
Design and extend systems to proactively benchmark, monitor, manage and optimise LLM selection, quantify drift in production, and measure cost vs. performance
-
Build APIs, data models, and tenant-aware authorization boundaries for workflows, executions, agents, connectors, inbox, dashboards, and configuration.
-
Create polished interfaces for workflow authoring, execution monitoring, review queues, dashboards, and configuration-heavy SaaS workflows.
-
Improve reliability through strong testing, runtime visibility, replay-safe changes, and careful debugging across UI, API, database, workers, and external services.
Who We’re Looking For
Required Experience
-
8+ years of professional software engineering experience, with strong ownership of production enterprise systems.
-
React experience, especially building complex data-heavy product interfaces
-
Experience with multi-tenant, distributed back-ends with mandatory authentication/authorization
-
Solid PostgreSQL experience, including schema design, migrations, query performance, transactional thinking, and gated data access.
-
Experience with durable or asynchronous systems: workflow engines, queues, jobs, event-driven systems, state machines, distributed orchestration.
-
Comfort debugging complex production behaviour across UI, backend, database, workers, and third-party integration layers.
-
Strong testing discipline and the ability to choose the right level of test for the risk involved.
Advantageous to have
-
Temporal.io experience, or comparable experience with durable workflows and replay-safe execution models.
-
Experience designing or maintaining workflow builders, automation platforms, rules engines, low-code tools, or developer-facing DSLs.
-
Experience identifying practical AI use cases inside business processes, especially where LLMs complement deterministic workflow logic.
-
Experience with AI/LLM integrations in production, including OpenAI, Anthropic, Gemini, structured outputs, tool use, agent patterns, or provider abstraction.
-
Experience with security-sensitive backend work: RLS, secure credential storage and tenant isolation
-
Experience with Kubernetes, Terraform, or other distributed orchestration systems
Core Competencies
-
Systems thinking: You can reason about frontend state, API contracts, database state, background execution, and external systems as one product.
-
Product-minded engineering: You care whether a feature meets the product requirements and is also understandable, simple to use, and operationally reliable
-
Autonomy and ownership: You can take a loosely defined problem, collaborate to discover the constraints, make good tradeoffs, and ship.
-
Clear communication: You can explain tradeoffs, document decisions, and collaborate well with product, design, AI, and engineering teammates.
-
Accountability and integrity: You take responsibility for outcomes, communicate transparently, and uphold high standards in both technical and team-impacting decisions.
Why Join
You’ll be joining a small, global team building a technically ambitious product at a stage where senior engineers can have a real impact. You will see work move quickly from idea to shipped product, and you will help define the architecture, quality bar, and engineering culture as we grow.
We value curiosity, clear thinking, accountability, and people who enjoy making complex systems feel simple for users.
To apply, please send your CV for the attention of Oleg at hiring@aguru.com with the subject line “Application for Senior Full Stack Engineer”. The application deadline is 30th June 2026.
Aguru is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all.
To apply: https://weworkremotely.com/remote-jobs/aguru-uk-ltd-senior-full-stack-engineer
URL: https://www.aguru.ai/
Senior Full Stack Engineer
Location: Remote, EU/UK preferred
Team: Engineering
Type: Full-time contractor
We are looking for a Senior Full Stack Engineer to join a small, high-impact engineering team. You will work across the product surface: React front end, NestJS backend, durable execution system, Postgres data layer and proprietary systems for evaluating and managing systems of LLMs. Some of this you may not have done before, but you will apply your transferable skills and experience!
This role suits someone who enjoys a variety of challenges, extending the forefront of what it takes to deliver reliable and trustworthy AI systems, and making those things simple and a joy to use. You will understand product needs, design clean domain models, build reliable components, ship easy-to-use interfaces, and debug distributed execution behaviour when things get interesting.
What You’ll Work On
-
Build product features across our React/Vite frontend, NestJS backend, PostgreSQL data layer, and Temporal-powered worker stack.
-
Develop new ways to benchmark and optimise LLM use, including error detection and correction and blocking AI-focused security attacks
-
Identify where AI can meaningfully improve structured tasks (and not make things worse): extraction, classification, decision support, agentic tool use, document understanding, communication handling, and automation of tedious operational steps.
-
Design and extend systems to proactively benchmark, monitor, manage and optimise LLM selection, quantify drift in production, and measure cost vs. performance
-
Build APIs, data models, and tenant-aware authorization boundaries for workflows, executions, agents, connectors, inbox, dashboards, and configuration.
-
Create polished interfaces for workflow authoring, execution monitoring, review queues, dashboards, and configuration-heavy SaaS workflows.
-
Improve reliability through strong testing, runtime visibility, replay-safe changes, and careful debugging across UI, API, database, workers, and external services.
Who We’re Looking For
Required Experience
-
8+ years of professional software engineering experience, with strong ownership of production enterprise systems.
-
React experience, especially building complex data-heavy product interfaces
-
Experience with multi-tenant, distributed back-ends with mandatory authentication/authorization
-
Solid PostgreSQL experience, including schema design, migrations, query performance, transactional thinking, and gated data access.
-
Experience with durable or asynchronous systems: workflow engines, queues, jobs, event-driven systems, state machines, distributed orchestration.
-
Comfort debugging complex production behaviour across UI, backend, database, workers, and third-party integration layers.
-
Strong testing discipline and the ability to choose the right level of test for the risk involved.
Advantageous to have
-
Temporal.io experience, or comparable experience with durable workflows and replay-safe execution models.
-
Experience designing or maintaining workflow builders, automation platforms, rules engines, low-code tools, or developer-facing DSLs.
-
Experience identifying practical AI use cases inside business processes, especially where LLMs complement deterministic workflow logic.
-
Experience with AI/LLM integrations in production, including OpenAI, Anthropic, Gemini, structured outputs, tool use, agent patterns, or provider abstraction.
-
Experience with security-sensitive backend work: RLS, secure credential storage and tenant isolation
-
Experience with Kubernetes, Terraform, or other distributed orchestration systems
Core Competencies
-
Systems thinking: You can reason about frontend state, API contracts, database state, background execution, and external systems as one product.
-
Product-minded engineering: You care whether a feature meets the product requirements and is also understandable, simple to use, and operationally reliable
-
Autonomy and ownership: You can take a loosely defined problem, collaborate to discover the constraints, make good tradeoffs, and ship.
-
Clear communication: You can explain tradeoffs, document decisions, and collaborate well with product, design, AI, and engineering teammates.
-
Accountability and integrity: You take responsibility for outcomes, communicate transparently, and uphold high standards in both technical and team-impacting decisions.
Why Join
You’ll be joining a small, global team building a technically ambitious product at a stage where senior engineers can have a real impact. You will see work move quickly from idea to shipped product, and you will help define the architecture, quality bar, and engineering culture as we grow.
We value curiosity, clear thinking, accountability, and people who enjoy making complex systems feel simple for users.
To apply, please send your CV for the attention of Oleg at hiring@aguru.com with the subject line “Application for Senior Full Stack Engineer”. The application deadline is 30th June 2026.
Aguru is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all.
To apply: https://weworkremotely.com/remote-jobs/aguru-uk-ltd-senior-full-stack-engineer
지원 기회 분석
지원 전에 볼 것
예상 산출물
- React/Vite 기반 워크플로우 저작·모니터링 UI
- 멀티테넌트 API 및 데이터 모델·인가 경계
- LLM 벤치마킹·드리프트·비용/성능 모니터링 시스템
- Temporal 기반 replay-safe 워커 실행 로직
매력 포인트
- 명확하고 상세한 기술 스펙
- 풀리모트(EU/UK 선호)
- 최신 AI/LLM 및 Temporal 등 매력적 기술스택
확인할 점
- 예산·급여 정보 미공개
- LLM 보안/드리프트 등 고난도 특수 영역 요구
Client signal
클라이언트 정보
플랫폼에서 상세 정보를 확인하세요.