Why Kimchi?

Kimchi is the AI platform inside CAST AI. We started by helping companies run LLMs on their own Kubernetes clusters - now we're building the execution layer where agents do real work.

Our Infrastructure today: multi-model inference (MiniMax, Kimi, GLM-5, Nemotron, DeepSeek) with intelligent routing, an OpenAI-compatible API, and deployment flexibility from our GPUs to your VPC. The inference layer is the foundation. What we're hiring for sits on top of it: coding agents, agent runtimes, orchestration systems, and the reliability engineering that makes them actually finish things.

Tech Stack: TypeScript, Go, Kubernetes, AWS/GCP/Azure, MCP, Prometheus/Grafana/Loki, GitLab CI, ArgoCD.

Why harness engineering matters here
OpenAI and Anthropic ship models. They also ship one harness each - the scaffolding that turns a raw model into something that can plan, execute, recover, and complete work. We ship a different kind of harness: one built for cost-conscious, long-horizon autonomy, running on inference infrastructure we control end-to-end.
A decent model with a great harness beats a great model with a bad harness. We've watched this play out. The gap between what today's models can do and what you see them doing is largely a harness gap - and that gap is where we operate.

What you'll build
The ratchet.
Every time our agent makes a mistake, we engineer a solution so it never makes that mistake again. That means hooks that enforce constraints the model "knows" but forgets: pre-commit lint checks, permission gates, context compaction before the window fills. Success is silent, failures are verbose.

Long-horizon execution.
Our harness is built around spec-driven autonomy: meta-prompting, fresh context per task, worktree-per-slice git strategy, automatic replanning, crash recovery, stuck detection. We're implementing Ralph loops - when the model tries to exit, we intercept and reinject the goal into a fresh context. The agent reads state from disk and continues. Multi-session, multi-day work, without context rot.

Planner/executor splits.
Planning with a reasoning model, executing with a fast one, evaluating with a third. Separating generation from evaluation beats self-verification because agents reliably skew positive when grading their own work.

The harness surface.
CLI, TUI, MCP integration, sandboxed execution, telemetry. Our AGENTS.md is short - every line traces to a specific thing that went wrong. TypeScript on the surface, Go where it matters.

Memory and context.
Moving agents off laptops, giving them state that survives across sessions, managing context so information lands where it's actionable. Compaction, tool-call offloading, progressive skill disclosure.

What makes this different (with receipts)
You've seen the pitch: "we route to the best model." Everyone says that. Here's what we actually have:

• GPU infrastructure we own. Not just an API reseller. From GPU placement across clouds to the inference endpoint your agent calls - we control the cost curve.
• A harness-first thesis. We treat agent failures as configuration problems, not model problems. When we moved from a stock harness to our own, completion rates on internal benchmarks improved by 40%+ on the same model.
• Agents.md that earns every line. No brainstormed rules - every constraint in our system prompt traces to a real failure we saw and fixed.

Requirements:

• You've used AI coding agents in anger. Not demos - real work. You have opinions about Claude Code, Codex, OpenCode, Cursor. You know what it feels like when an agent gets stuck and why.
• Strong TypeScript or Go in production. Comfort moving between them. Our surface is TypeScript; our core is Go.
• You think in harness terms. You read "the agent hallucinated" and your first instinct is to ask what context it was missing, what hook should have caught it, what constraint should exist.
• You drive features end-to-end. Design → build → ship → measure → iterate. We don't have layers that absorb ambiguity for you.

Responsibilities:

• Build and evolve the agent harness - ship hooks, permission gates, and context compaction. Every AGENTS.md constraint traces to a failure you personally diagnosed.
• Own long-horizon execution - multi-session task completion via spec-driven prompting, worktree-per-slice git, Ralph loop recovery, and stuck detection. Completion rate is your metric.
• Architect planner/executor/evaluator pipelines - planning with a reasoning model, execution with a fast one, evaluation with a third. No self-verification.
• Manage agent memory and context - state persistence across sessions, context compaction, tool-call offloading. Zero context rot on multi-day work.
• Own the harness surface - CLI, TUI, MCP integrations, sandboxed execution, telemetry. TypeScript on the surface, Go where it matters.

What success looks like (after 6 months):

• You've shipped at least one major harness feature end-to-end: designed it, built it, measured it, iterated.
• You've added constraints to our AGENTS.md based on failures you personally observed and diagnosed.
• You've improved a measurable reliability metric - completion rate, context efficiency, or cost per successful task.
• You've formed strong opinions about where our harness is load-bearing and where it's dead weight.

What’s in it for you?

• Competitive salary (€6,500 - €9,000 gross, depending on the level of experience).
• Enjoy a flexible, remote-first global environment.
• Collaborate with a global team of cloud experts and innovators, passionate about pushing the boundaries of Kubernetes technology
• Equity options.
• Get quick feedback with a fast-paced workflow. Most feature projects are completed in 1 to 4 weeks.
• Spend 10% of your work time on personal projects or self-improvement. 
• Learning budget for professional and personal development - including access to international conferences and courses that elevate your skills.
• Annual hackathon to spark new ideas and strengthen team bonds.
• Team-building budget and company events to connect with your colleagues.
• Equipment budget to ensure you have everything you need.
• Extra days off to help maintain a healthy work-life balance.

This is a location-specific opportunity. We are currently accepting applications from candidates residing in the following European countries: Bulgaria, Croatia, Estonia, Greece, Hungary, Latvia, Lithuania, Poland, Romania, Slovakia, Slovenia, and Ukraine.

*As part of our standard hiring process, we would like to inform you that a background check may be conducted at the final stage of recruitment through our third-party provider, Checkr.
*Please note that Cast AI does not provide any form of visa sponsorship/work permit.

#LI-Remote

Our Partner

Our partner is a fast-growing software company that builds networks like clouds. It offers communications service providers and cloud providers a radical new way to build networks, detaching network growth from network cost and increasing network profitability.

Our partner’s Network Cloud solution uniquely supports the complete virtualization of network and compute resources, enabling communication service providers and cloud providers to meet increasing service demands much more efficiently than with today’s monolithic routers.

Their software runs over standard white-box hardware and can easily scale network capacity by adding additional white boxes into physical network clusters. This unique disaggregated network model enables the physical infrastructure to operate as a shared resource that supports multiple networks and services. This unique network design also allows faster service innovation at the network edge, supporting multiple service payloads, including latency-sensitive ones, over a single physical network edge.

Role Overview

We are seeking a DevTest Engineer with a strong QA mindset and a passion for networking, who is not afraid to use AI‑driven tools to elevate and modernize testing practices. The ideal candidate thrives in a dynamic environment, takes ownership of quality, and actively applies modern technologies to enhance automation, efficiency, and overall testing impact.
We are looking for the best of the best talent that is capable of dreaming out of the box and can execute on the dream and turn it into real value for our customers.

Responsibilities

• Own QA testing activities as part of a Scrum team in an Agile environment.
• Design, write, and execute test plans; lead TP reviews; report and verify issues.
• Contribute to PI planning and define QA scope and activities within the team.
• Participate in daily meetings, proactively raising risks and blockers.
• Collaborate closely with Dev, DevTest, Product, and Architecture to deliver high-quality features.
• Develop and maintain automated tests in a Python environment.
• Triage and analyze failures from automation regression runs.
• Actively use AI-based tools to improve testing efficiency, coverage, and debugging.
• Contribute to improving test frameworks, methodologies, and QA processes

Requirements

Must have:

• Bachelor’s degree in computer science, engineering, or related field (or equivalent experience).
• At least 2 years of experience in QA Networking, or 5 years of experience in Networking Routing.
• Deep understanding in routing protocols: ISIS/OSPF, BGP.
• Network Knowledge: L2, L3, MPLS/LDP.
• Experience in test automation using Python (preferred), Java, or JavaScript, including working with frameworks such as pytest.
• Scripting capabilities (e.g., Bash/Python).
• Strong troubleshooting and root cause analysis skills.
• Experience with CI/CD tools (e.g., Jenkins, GitHub Actions, GitLab CI).
• Hands-on experience with AI coding assistants (e.g., Cursor, GitHub Copilot) or similar tools.
• Familiarity with LLMs and prompt engineering.
• Strong English communication skills (verbal and written).
• Willing to adapt and learn new things.

Nice to have:

• Minimum 2 years of experience in QA position.
• Experience with writing test plans and performing manual/automated tests.
• Familiarity with traffic generators (Ixia, Spirent).
• Segment-Routing, RSVP, L2VPN, L3VPN, Multicast– strong advantage.
• Experience with Ixia/Spirent tool.
• Linux knowledge: deep knowledge/experience with Linux.
• Experience with Docker or containerized environments.
• Experience working with Jira in Agile mode.
• Autodidact.
• Multitasking.

Reasons to Work with Us

• Competitive financial conditions.
• Opportunity to work on internationally recognized projects.
• Flexible schedule and a hybrid work model, prioritizing remote work as much as possible to support work-life balance.
• An exciting career path within a friendly, dynamic, and growing organization.
• Professional development opportunities in a multicultural environment.
• Private medical coverage with Medlife or Regina Maria.
• Meal vouchers.
• Gift vouchers for special occasions such as birthdays, weddings, or childbirth.
• Wellbeing programs, including sick days, 7Card subscriptions, and relaxation facilities in the office.
• Team-building events and other social experiences.
• Budget allocated for certifications relevant to your project.
• Workshops, internal training sessions, and knowledge-sharing opportunities.
• Convenient city-center office location.
• Shared parking spaces.

As a global digital transformation company, Orion values creating a productive, diverse work environment. We are committed to maintaining a positive work environment where our people value traits that make each one of us different from one another. We all bring a diverse set of perspectives, work and life experiences, and our differences make us more valuable both internally and for our clients.

ZAM Network is a multi-faceted company based in the United States. We specialize in building engaged gaming communities through its three core pillars of marketing, creative services and user research. ZAM operates one of the largest gaming networks in the world including the #1 community for World of Warcraft, Wowhead. 

Wowhead was created with one sole intent: providing World of Warcraft players with tools and information to make their gameplay more enjoyable. All staff members are passionate fans of World of Warcraft, which helps us keep abreast of the most important features other players are interested in! We pride ourselves on our comprehensive database with helpful user comments, popular tools like the Dressing Room and Flying Tracker, lightning-fast datamining to uncover the latest test realm updates, and detailed guides written by professional players on all popular WoW topics including classes, collections, secrets, and raids. We’ve branched out to cover the Diablo franchise and are planning our next stage of growth.

We are currently seeking a Reverse Engineer with extensive data mining experience to join our team as an independent contractor. This is not an entry level role and you will be working to extract both static and runtime game data for World of Warcraft to help Wowhead to expand our current tools to aid our community of gamers. This position is a full-time remote as you will collaborate with the entire Wowhead team as we work together to deliver world-class products to our fans.

Key Responsibilities

• Manage development of the Wowhead Studio application, to facilitate datamined assets of creatures, characters, and other in-game objects
• Extract game data and game assets required to build tools to support our products and services.
• Maintain Wowhead’s model tools using the site’s WebGL model viewers. TypeScript-based standard viewer used in most of Wowhead website.
• Use C++ web assembly-based viewer that is faster with accurate lighting, for various World of Warcraft Player Housing pages.
• Use JavaScript-based Three.js model viewer.
• Maintain comprehensive technical documentation on game data (contents, formats, change history), data mining tools and processes employed, and anything else related to the role.
• Communicate consistently, clearly, and efficiently all assigned task progress, blockers, or any other role-related issues in a prompt and professional manner on a regular basis.

Experience and Technical Requirements

• Previous hands-on experience doing data mining work on World of Warcraft and/or Diablo IV. This is not a “learn as you go” type of role; we operate in a fast paced, highly competitive, and challenging environment.
• Comprehensive understanding using various programming languages (such as C++, Python, C#, TypeScript and JS) in order to choose the best tool for the job.
• Understanding of various debugging, reverse engineering, and custom made tools to accomplish assigned tasks.
• Ability to read and comprehend x86/x64 assembly language, such as via IDA as this role is not solely a “file format” data mining role.
• Strong communication skills in English, both written and verbal, with the ability to convey information clearly and effectively.
• A collaborative mindset; ability to collaborate remotely and coordinate with stakeholders across different time zones.
• Professionalism, reliability, and a commitment to delivering high quality work utilizing your analytical and problem-solving skills.
• Being experienced in Blizzard games will make it easier to understand project requirements and the consumer side.