Kozak Agency

Frontend-Developer (React) for client (German multinational energy enterprise)

We are looking for a strong Frontend-Developer with expertise in React.
Start: asap
Duration: 6 months + option for extension
Workload: Full-time
Location: 100% Remote/Offsite; no Onsite
Project language: English

We are looking for a skilled fullstack developer to support the further development of a production-grade web application. The stack includes Angular (latest version) as the frontend framework, NestJS for the backend, MariaDB as the database, and Keycloak for authentication and authorization. We use TypeORM for data access.

Responsibilities:

• Build and maintain Angular components (standalone components, Signals)
• Extend and improve REST APIs using NestJS
• Manage the MariaDB database schema and migrations using TypeORM
• Implement and maintain Keycloak-based authentication, including role-based access control
• Write end-to-end tests using Playwright or Cypress
• Ensure high code quality and contribute to technical documentation

Requirements:

• Strong experience with Angular (v16 or newer), including Signals
• Proficiency with NestJS and modular backend architecture
• Solid TypeScript knowledge
• Hands-on experience with MariaDB and TypeORM
• Real-world experience integrating Keycloak into fullstack apps
• Experience with Playwright or Cypress for end-to-end testing
• Familiarity with Docker, Git, and CI/CD pipelines

Project Info:

• The application is already live and actively used
• Tasks are well-defined and managed via GitHub
• Collaboration with an internal development team
• Modern, containerized infrastructure
• We’re looking for someone who can get started soon. If the collaboration works well, long-term cooperation is possible.

We’re looking for an Applied AI Engineer who combines strong ML fundamentals with the discipline of improving production AI systems through metrics, evaluation, and iteration.

Details:
Senior AI/ML Engineer, ideally 5 years of experience. Ready to consider candidates starting with 3 years of experience, but they must be very strong in AI/ML.
Strong proficiency in English (Upper-intermediate level or Advanced)
Full-time
Location: any
Start: ASAP!

The role in a nutshell
You’ll work on improving production AI systems through evaluation, experimentation, and system design.

A large part of the role involves:

diagnosing failures in agent workflows
designing evaluation metrics and KPIs
improving system prompts and agent behavior
running structured experiments and measuring impact
You won’t be working in isolation on research projects — you’ll be improving systems that real users depend on.

Rough responsibility breakdown:

AI evaluation and KPI design — ~30%
Prompt and agent system design — ~30%
ML systems (recommendation, optimization, etc.) — ~30%
Engineering integration — ~10%

What you’ll work on:

AI evaluation and system quality

Design evaluation strategies for LLM and agent workflows
Create metrics and KPIs for AI system performance
Build and maintain evaluation datasets
Debug production AI failures systematically
Compare system behavior against baselines
This is a core responsibility of the role.

Multi-agent AI systems

Improve agent orchestration and workflows
Diagnose failures across agent pipelines
Refine system prompts and agent interactions
Improve reliability, latency, and response quality of ML and AI systems

You’ll contribute to areas such as:

Recommendation systems (ranking and personalization)
Itinerary optimization and constraint-based planning
LLM-based reasoning systems
Optional: computer vision pipelines
Depth in one of these areas is more important than superficial experience in all of them.

Engineering collaboration
We use:

Golang (primary production language)
Python when necessary for ML workflows
Postgres, Redis, and internal services
You don’t need to be a Go expert on day one, but you should be comfortable reading and modifying production code.
Backend engineers handle infrastructure-heavy service development — your focus is on AI system behavior and correctness.

What we’re looking for
Must-haves
1. Strong AI/ML fundamentals
You understand the theory behind what you build and can choose appropriate methods for a problem.
Examples:

evaluation metrics (precision/recall/F1/etc.)
ranking and recommendation concepts
embeddings and similarity
experimentation methodology

Not required:
academic publications
advanced theoretical math
large-scale model training experience

2. Evaluation-driven mindset You:

think in metrics and baselines
design experiments instead of guessing
measure system improvements quantitatively
debug failures methodically
This is the most important signal for the role.

3. Experience with LLM systems you’ve worked with:

prompt design
agent workflows
evaluation of LLM outputs
production LLM integrations

4. Ability to ship production systems
You can:

turn ideas into working systems
iterate based on results
balance exploration with delivery

5. Programming ability You’re comfortable writing production code in at least one language (Python, Go, or similar) and learning others when needed.

Strong signals (nice to have)
Experience improving an AI system after deployment
Recommendation systems or ranking experience
Optimization or constraint-based systems
Computer vision experience
Experience building evaluation frameworks
Golang experience
Startup or small-team engineering experience

Responsibilities

• Deployment and maintenance of production Kubernetes clusters (Kubespray)
• Ensuring High Availability (HA) for control plane, etcd, and stateful services
• IAM and security management (Keycloak, RBAC, Network Policies)
• Setup and maintenance of monitoring, logging, and alerting systems
• Support of development environments (Minikube)
• Incident response and participation in platform stability improvements
   

Requirements

Must have:

• Strong hands-on experience with Kubernetes in production environments
• Practical experience with Kubespray
• Docker / containerd
• Experience with stateful workloads (PostgreSQL, Redis)
• Helm, Git, Bash
• Monitoring stack experience (Prometheus, Grafana)
• Solid understanding of Kubernetes networking (Ingress, Services, NetworkPolicy)
   

Nice to have:

• Experience with Keycloak (OIDC, LDAP, RBAC)
• Experience with Longhorn or Rook-Ceph
• Experience with EFK stack (Fluentd, Elasticsearch, Kibana)
• Experience with HashiCorp Vault
• Experience with MinIO / S3-compatible storage
• Understanding of SRE practices (SLA / SLO principles)

Requirements
• Strong proficiency in SQL
• Solid experience with Python
• Commercial experience as a Data Engineer / Python Developer
• Hands-on experience with data migration and database processes
• Ability to work independently and ensure data consistency
• English: B2+

• Duration: 3–5 months
• Start: ASAP


We offer:

• Cooperation with a stable company with well-established processes and a positive atmosphere
• Experience in project management of different levels of complexity, methodology, and approaches
• Flexible schedule: Mon-Fri (8 hours a day)
• 18 days of paid vacation; 15 days sick leave
• A decent level of remuneration with regular reviews of the results of cooperation
• Extensive loyalty program 

Strong focus on React (around 70%) with additional experience in .NET and Azure (around 30%).
 

We’re looking for a Middle+ to Senior level engineer who is confident on the frontend side and comfortable working with backend services and cloud infrastructure.
 

Ready to start quickly.

Preferably with experience in apple/google TV apps.

We already have and Android and iOS apps with video content, and we need to extend them to Apple TV and Google TV without distracting the core team.

We’re building these TV apps because we plan to apply for the Apple and Google video programs.

 

application process via test task and then interview with head of engineering

We don't need coders, we need Golang backend engineers who build features end-to-end using Claude Code.

Details:
• AI coding experience (mandatory!): experience with Claude Code - #1 priority, or other agentic coding tools. Claude Code is what is used on the project
• Senior Golang Developer, 5+ years of experience, can potentially consider really strong candidates with 4 years of experience
 • Strong proficiency in English (Upper-intermediate level or Advanced)
 •
 • Full-time
 • Fully remote
 • Start: ASAP!
 • Duration: long-term

Sharing more details about the responsibilities and requirements below.

What you'll actually do:
 • Own features end-to-end: from specs to deployment to fixing bugs
 • Use Claude Code to generate Golang backend code
 • Review AI output for quality and architectural fit
 • Fix bugs to learn our codebase, then rapidly build new features
 • Make quick decisions on what to build vs buy vs generate with AI
 • Talk to customers when they report issues and ship fixes same day

Our stack:
 • Backend: Golang monorepo
 • AI: Claude Code (mandatory), other agentic coding tools

Products you will build:
 • API: platform features, tooling, multi-agent system, etc.

You must have:
 • Ownership mentality with a strive for elegantly simple, high-quality solutions
 • Strive for max quality - you test your own work thoroughly since we have no QA team, everything you ship MUST work
 • Product mindset - you care about WHY we're building something
 • Proven experience using Claude Code or similar agentic AI (Cursor, Windsurf)
 • Strong Golang experience - you'll review AI's code in these, and you must understand how it works
 • Broad architectural knowledge of building backened

 

We are looking for an AI-First Product Engineer (Full-Stack): SvelteKit Frontend, Golang Backend. 
We don't need coders, we need engineers who build features end-to-end using Claude Code. Without any "hand-coding".

Details:
• AI coding experience (mandatory!): experience with Claude Code - #1 priority, or other agentic coding tools. Claude Code is what is used on the project
• Senior Full-Stack Engineer (SvelteKit Frontend, Golang Backend), 5+ years of experience, can potentially consider really strong candidates with 4 years of experience
 • Strong proficiency in English (Upper-intermediate level or Advanced)
 • Full-time
 • Fully remote

Sharing more details about the responsibilities and requirements below.

What you'll actually do:
 • Own features end-to-end: from specs to deployment to fixing bugs
 • Use Claude Code to generate SvelteKit frontend and Golang backend code
 • Review AI output for quality and architectural fit
 • Fix bugs to learn our codebase, then rapidly build new features
 • Make quick decisions on what to build vs buy vs generate with AI
 • Talk to customers when they report issues and ship fixes same day

Our stack:
 • Frontend: SvelteKit, turbo monorepo, Vercel
 • Backend: Golang monorepo
 • AI: Claude Code (mandatory), other agentic coding tools

Products you will build:
 • API: platform features, tooling, multi-agent system, etc.
 • UIs: internal UIs, B2B dashboards, B2C web apps

You must have:
 • Ownership mentality with a strive for elegantly simple, high-quality solutions
 • Strive for max quality - you test your own work thoroughly since we have no QA team, everything you ship MUST work
 • Product mindset - you care about WHY we're building something
 • Proven experience using Claude Code or similar agentic AI (Cursor, Windsurf)
 • Strong SvelteKit and Golang experience - you'll review AI's code in these, and you must understand how it works
 • Broad architectural knowledge of building modern full-stack applications
 • Excellent spoken English and a good internet connection for daily video calls

You are a great fit if you:
 • Get frustrated when development takes weeks instead of days
 • You think in features and architecture and not single lines of code
 • Can spot subtle bugs in AI-generated code quickly
 • You ship fast but always verify it actually works
 • Have shipped real products that customers actually use
 • Think "how can AI build this?" as your first instinct

Red flags (don't apply if):
 • You've never used Claude Code or similar AI coding tools
 • You're a perfectionist who loves to code
 • You need detailed specs before starting
 • You see AI as a threat rather than leverage
 • You're outside European/African time zones

Preferably with experience in apple/google TV apps.

We already have and Android and iOS apps with video content, and we need to extend them to Apple TV and Google TV without distracting the core team.

We’re building these TV apps because we plan to apply for the Apple and Google video programs.
 

the project is outstaff for roughly 4 months
 

application process via test task and then interview with head of engineering

We don't need coders, we need engineers who build features end-to-end using Claude Code. Without any "hand-coding".

Details: 
 • AI coding experience (mandatory!): experience with Claude Code - #1 priority, or other agentic coding tools. Claude Code is what is used on the project 
• Senior Full-Stack Engineer (SvelteKit Frontend, Golang Backend), 5+ years of experience, can potentially consider really strong candidates with 4 years of experience 
• Strong proficiency in English (Upper-intermediate level or Advanced)
 • Full-time
 • Fully remote
 • Start: ASAP!

Sharing more details about the responsibilities and requirements below.

What you'll actually do:
 • Own features end-to-end: from specs to deployment to fixing bugs
 • Use Claude Code to generate SvelteKit frontend and Golang backend code
 • Review AI output for quality and architectural fit
 • Fix bugs to learn our codebase, then rapidly build new features
 • Make quick decisions on what to build vs buy vs generate with AI
 • Talk to customers when they report issues and ship fixes same day

Our stack:
 • Frontend: SvelteKit, turbo monorepo, Vercel
 • Backend: Golang monorepo
 • AI: Claude Code (mandatory), other agentic coding tools

Products you will build:
 • API: platform features, tooling, multi-agent system, etc.
 • UIs: internal UIs, B2B dashboards, B2C web appsYou must have:
 • Ownership mentality with a strive for elegantly simple, high-quality solutions
 • Strive for max quality - you test your own work thoroughly since we have no QA team, everything you ship MUST work
 • Product mindset - you care about WHY we're building something
 • Proven experience using Claude Code or similar agentic AI (Cursor, Windsurf) 
 • Strong SvelteKit and Golang experience - you'll review AI's code in these, and you must understand how it works
 • Broad architectural knowledge of building modern full-stack applications
 • Excellent spoken English and a good internet connection for daily video calls

You are a great fit if you:
 • Get frustrated when development takes weeks instead of days
 • You think in features and architecture and not single lines of code
 • Can spot subtle bugs in AI-generated code quickly
 • You ship fast but always verify it actually works
 • Have shipped real products that customers actually use
 • Think "how can AI build this?" as your first instinct

Red flags (don't apply if):
 • You've never used Claude Code or similar AI coding tools
 • You're a perfectionist who loves to code
 • You need detailed specs before starting
 • You see AI as a threat rather than leverage
 • You're outside European/African timezones