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

RSI is seeking a Database Architect to help shape and grow the company's database platform and capability through guidance, enablement, and collaboration. This role works alongside DBAs, engineers, and analytics teams to develop shared standards, foster good architectural thinking, and help teams make confident, well-informed decisions about database design across both relational and non-relational technologies.

A key focus of the role is helping teams understand and adopt data contracts, versioned agreements that describe schemas, semantics, quality expectations, SLAs, and change policies. Rather than mandating compliance, the Architect acts as a trusted advisor and internal expert, building the knowledge and tooling that makes doing the right thing the easy thing.

The Database Architect works closely with database engineering, product engineering, infrastructure platform, and BI & Analytics teams, influencing through expertise, mentorship, and practical enablement. While organizationally sitting within the Architecture team, this role has a dotted-line relationship to the Database Engineering Manager, ensuring tight day-to-day collaboration with the engineering team and a shared stake in their growth and success.

What You'll Do:

Architecture and Standards

• Develop and share database architecture patterns and best practices across both relational and non-relational technologies covering schema design, data modelling, high availability, disaster recovery, and performance, offering guidance teams can draw on rather than directives they must follow.
• Help teams select the right database technology for their use case, whether relational, document, key-value, graph, or time-series, based on access patterns, scale, and consistency requirements.
• Lead collaborative efforts to define data contracts for in-house products, working with teams to shape schemas, semantics, quality expectations, change policies, and SLAs in a way that makes sense for their context and chosen technology.
• Create decision frameworks and reference materials that help teams design compliant and scalable database solutions independently.

Governance and Data Quality

• Champion data contract principles by helping teams understand their value and how to apply them with a focus on reducing risk for downstream consumers through shared understanding, not top-down enforcement.
• Partner with Analytics, product, and security teams to explore how contract metadata, validations, and policy checks can be woven into CI/CD pipelines and production workflows in practical, low-friction ways.
• Support teams in managing versioning, deprecation, and change notifications, helping them build sustainable habits around schema evolution, including schema-on-read and flexible schema patterns common in non-relational systems.

Cross-Team Collaboration

• Join architecture and design conversations early in the development lifecycle, offering a perspective that helps teams spot risks and opportunities before they become problems.
• Work alongside engineers and DBAs to integrate data contracts into tooling and monitoring, making traceability and observability a natural part of how teams work rather than an afterthought.

Enablement and Coaching

• Mentor engineers and DBAs on data contract design, from schema stability to SLA definition, building genuine understanding of the downstream impact of their decisions.
• Develop reusable frameworks, templates, and examples for data contracts that teams can adapt and build on, reducing the barrier to doing things well.
• Serve as a go-to resource and sounding board on database architecture topics, both relational and non-relational, helping individuals and teams grow their expertise over time.

What You'll Bring:

• Bachelor’s or Master’s degree in Computer Science or related field.
• 5+ years of experience in database design, data modelling or database engineering roles with a strong relational foundation and exposure to non-relational systems.
• Strong expertise in relational databases (PostgreSQL, Oracle preferred), including a solid understanding of RDBMS internals, performance considerations, and architectural trade-offs.
• Experience with database architecture design patterns, data modelling standards, high-availability strategies, and schema evolution.
• Familiarity with non-relational database technologies such as document stores, key-value stores, wide-column stores, graph databases, and time-series databases and an understanding of when and why to reach for them over a relational approach.
• Awareness of polyglot persistence approaches and how to govern data contracts across mixed database environments.
• Comfortable working in cloud-first or hybrid environments.
• Excellent communication and interpersonal skills — able to explain complex technical concepts clearly to a range of audiences and build trust with both technical and non-technical stakeholders.
• A collaborative, patient approach to working with teams, with a genuine interest in helping others develop their skills and confidence.
• Able to travel occasionally both domestically and internationally #LI-REMOTE #LI-PROMOTE

About the Role:  

Wrike’s Backend Reliability (BRE) team is the backbone of our backend infrastructure and the guardian of our uptime. Our mission is to achieve and sustain 99.99% availability while building the tools, components, and safety nets that the entire engineering organization relies on. As a Senior / Staff Backend Engineer on this team, you won’t just close tickets - you’ll architect core reliability solutions that shape how Wrike scales, performs, and recovers from failure.

Your Impact:  

• Design, build, and maintain critical reliability components such as HTTP rate limiters, internal DB schema migration tools, circuit breakers, and distributed Redis-based caching.  
• Troubleshoot complex production issues, optimize PostgreSQL usage, and ensure our distributed systems remain performant and stable under high load.  
• Lead preliminary investigations during severe production incidents: identify likely root causes, assess impact, and propose mitigation options. The long-term fixes are then implemented by the owning team, based on your findings.  
• Create scalable, reusable tools and frameworks that help other engineering teams build more resilient services.  
• Leverage AI-powered tools and coding agents to accelerate development, analyze architectures, and automate repetitive or error-prone tasks.  
• Influence reliability best practices across engineering by sharing knowledge, reviewing designs, and setting high technical standards.

Your Qualifications:  

• Strong expertise with Java/JVM, building scalable, high-performance backend systems; open to leveraging other languages when appropriate.  
• Solid understanding of distributed systems concepts, including high availability, CAP theorem, and fault tolerance.  
• Deep experience with relational databases (PostgreSQL) and key–value / non-relational storages (Redis).  
• Practical experience with containerization and cloud-native environments, including Docker and Kubernetes.  
• Hands-on experience with message brokers such as RabbitMQ or Kafka.  
• Ability to work independently with minimal supervision, using critical thinking to question assumptions and validate your own decisions.  
• Strong written and spoken English skills suitable for collaborating in an international engineering environment.

Standout Qualities:  

• Background in infrastructure engineering or Site Reliability Engineering (SRE), including infrastructure-as-code practices.  
• Experience leading technical initiatives, driving cross-team projects, and mentoring other engineers while remaining an individual contributor.  
• Familiarity with observability and monitoring stacks (e.g., Graylog, Zabbix, Grafana) and/or data analytics tools such as BigQuery.  
• A strong interest in how complex systems fail and a track record of designing them to recover gracefully.

Team Dynamics:  

You will join the Backend Reliability (BRE) team, a small, highly specialized, senior group focused solely on Wrike’s reliability. The team operates as an internal “reliability task force,” partnering closely with product and platform engineering teams across the company. You’ll collaborate with other senior engineers who value autonomy, deep technical discussions, and rigorous engineering practices. The culture is ownership-driven: you are trusted to manage your time, make architectural decisions, and drive initiatives to completion.

Our Work Style:  

The BRE team works on core backend and infrastructure services that support millions of users. We operate in a collaborative environment that values clear communication, thoughtful design, and fast feedback loops.  

• Tech focus areas include: Java/JVM-based services, PostgreSQL, Redis, Docker, Kubernetes, RabbitMQ/Kafka, and observability/monitoring tools.  
• We encourage the use of modern AI-based tooling and coding agents as part of daily development and troubleshooting workflows.  
• Work is organized with an emphasis on impact and reliability goals rather than ticket volume, giving you room for deep work and long-term improvements.  
• Hybrid work mode (Prague, Czech Republic / Nicosia, Cyprus), with flexibility to balance focused individual work and collaborative sessions.

Why Join Wrike?

• 5 Weeks of paid vacation
• Sick Leave Compensation 
  • 5 Paid Uncertified Sick Days
  • 2 weeks fully paid w/ medical certificate, additional 
  • 4 weeks paid at 80% salary rate
• Parental Leave (fully paid): 18 Weeks Maternity / 4 Week Paternity 
• 2 Volunteer Days
• Meal Vouchers (CZK 220 per working day)
• Annual Prague Travel Card (Lítačka)
• Hybrid Working Model
• Benefit budget with flexible options, including a MultiSport card, Canadian Medical membership, contributions to a pension savings plan and additional choices available through Benefit Plus

What’s next?

• Interview with a Recruiter
• Technical interview
• System Design Interview
• Cultural interview 
  

Your recruitment buddy will be Aleksandar Chernev, Senior Technical Recruiter.

#LI-AC1 

About the Role:  

Wrike’s Backend Reliability (BRE) team is the backbone of our backend infrastructure and the guardian of our uptime. Our mission is to achieve and sustain 99.99% availability while building the tools, components, and safety nets that the entire engineering organization relies on. As a Senior / Staff Backend Engineer on this team, you won’t just close tickets - you’ll architect core reliability solutions that shape how Wrike scales, performs, and recovers from failure.

Your Impact:  

• Design, build, and maintain critical reliability components such as HTTP rate limiters, internal DB schema migration tools, circuit breakers, and distributed Redis-based caching.  
• Troubleshoot complex production issues, optimize PostgreSQL usage, and ensure our distributed systems remain performant and stable under high load.  
• Lead preliminary investigations during severe production incidents: identify likely root causes, assess impact, and propose mitigation options. The long-term fixes are then implemented by the owning team, based on your findings.  
• Create scalable, reusable tools and frameworks that help other engineering teams build more resilient services.  
• Leverage AI-powered tools and coding agents to accelerate development, analyze architectures, and automate repetitive or error-prone tasks.  
• Influence reliability best practices across engineering by sharing knowledge, reviewing designs, and setting high technical standards.

Your Qualifications:  

• Strong expertise with Java/JVM, building scalable, high-performance backend systems; open to leveraging other languages when appropriate.  
• Solid understanding of distributed systems concepts, including high availability, CAP theorem, and fault tolerance.  
• Deep experience with relational databases (PostgreSQL) and key–value / non-relational storages (Redis).  
• Practical experience with containerization and cloud-native environments, including Docker and Kubernetes.  
• Hands-on experience with message brokers such as RabbitMQ or Kafka.  
• Ability to work independently with minimal supervision, using critical thinking to question assumptions and validate your own decisions.  
• Strong written and spoken English skills suitable for collaborating in an international engineering environment.

Standout Qualities:  

• Background in infrastructure engineering or Site Reliability Engineering (SRE), including infrastructure-as-code practices.  
• Experience leading technical initiatives, driving cross-team projects, and mentoring other engineers while remaining an individual contributor.  
• Familiarity with observability and monitoring stacks (e.g., Graylog, Zabbix, Grafana) and/or data analytics tools such as BigQuery.  
• A strong interest in how complex systems fail and a track record of designing them to recover gracefully.

Team Dynamics:  

You will join the Backend Reliability (BRE) team, a small, highly specialized, senior group focused solely on Wrike’s reliability. The team operates as an internal “reliability task force,” partnering closely with product and platform engineering teams across the company. You’ll collaborate with other senior engineers who value autonomy, deep technical discussions, and rigorous engineering practices. The culture is ownership-driven: you are trusted to manage your time, make architectural decisions, and drive initiatives to completion.

Our Work Style:  

The BRE team works on core backend and infrastructure services that support millions of users. We operate in a collaborative environment that values clear communication, thoughtful design, and fast feedback loops.  

• Tech focus areas include: Java/JVM-based services, PostgreSQL, Redis, Docker, Kubernetes, RabbitMQ/Kafka, and observability/monitoring tools.  
• We encourage the use of modern AI-based tooling and coding agents as part of daily development and troubleshooting workflows.  
• Work is organized with an emphasis on impact and reliability goals rather than ticket volume, giving you room for deep work and long-term improvements.  
• Hybrid work mode (Prague, Czech Republic / Nicosia, Cyprus), with flexibility to balance focused individual work and collaborative sessions.

Why Join Wrike?

• 25 calendar days of paid vacation
• Sick Leave Compensation (5 Paid Uncertified Sick Days)
• Parental Leave: 18 Weeks Maternity / 4 Week Paternity 
• 2 Volunteer Days
• Medical Insurance (Employees + Dependents)
• Hybrid Working Model
• School Allowance (Up to €600/month for school aged kids)
• Simcard w/ Unlimited Internet Access for active employees
• Office Lunch Allowance (via Wolt) on Wednesdays / Thursdays

What’s next?

• Interview with a Recruiter
• Technical interview
• System Design Interview
• Cultural interview 
  

Your recruitment buddy will be Aleksandar Chernev, Senior Technical Recruiter.

#LI-AC1