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

Bloomreach powers digital commerce with AI-native solutions for marketing automation, search and merchandising, conversational shopping assistance, and headless content management—driven by unified customer and product data for personalization and measurable business impact. We're expanding with new ideas and modules.

For example, our Autonomous marketing solution, you can get more info about our vision here -  https://visit.bloomreach.com/innovation-fest-2025-after

Join the Engineering team working on an Autonomous marketing solution to help shape the future of autonomous marketing. As a Software Engineer, you'll build and deploy agentic AI systems with real-world impact, collaborating alongside innovators redefining how brands engage millions of customers.

If you're passionate about prompt and context engineering, driven by impact, and want to be a key part of defining the industry's future, Bloomreach wants to hear from you. This role focuses on solving real-world problems with production-ready agentic systems, not just internal experimentation.

What challenge awaits you?

Step into the forefront of autonomous marketing innovation. As a member of the Engineering team, you’ll take on the challenge of designing, developing, and scaling production-grade agentic AI systems that are redefining how brands connect with millions of customers in real time.

You will tackle the complexities of architecting and orchestrating powerful AI agents—leveraging the latest in large language models, prompt and context engineering, and agentic workflows—to drive automated, personalized engagement across diverse digital channels. Your work involves shaping the context and memory that empowers our agents to make smart, data-driven decisions at scale.

Collaboration is key: you’ll partner with fellow engineers, data scientists, and product leaders to integrate agentic intelligence into our platform, ensuring seamless alignment with customer data, analytics, and channel experiences. This is a unique opportunity to apply your technical expertise in prompt and context engineering, contribute to an ambitious product vision, and help define the future of the marketing industry through autonomous, AI-driven solutions.

What will you do?

• Design and deliver meaningful, production-grade features end-to-end, always anchored in clear user needs and measurable business value. You’ll translate high-level vision and customer requirements into actionable plans, robust code, and scalable solutions.
• Define technical specifications directly from business goals and work collaboratively with product managers, engineers, QAs, and data scientists to ensure that every build solves a concrete problem for users.
• Build and ship APIs and backend components that drive agentic workflows and seamless AI-powered automation—ensuring performance, security, and maintainability at scale.
• Integrate and operationalize state-of-the-art GenAI, LLMs, and orchestration frameworks so your agents take real business actions in production environments, not just in proofs-of-concept.
• Take full accountability for the robustness of your solutions: developing comprehensive test suites, rigorous evaluation frameworks (including agent- and system-level benchmarking), and monitoring strategies to ensure reliability and measurable outcomes. You'll evaluate both automated agentic behaviors and overall system performance to guarantee these systems perform as intended in live scenarios.
• Apply your full stack of skills—ranging from software engineering and prompt/context design to real-world LLM/GenAI operations and DevOps best practices. You’ll make agentic systems functional, maintainable, and resilient from dev environments through to production and post-launch.
• Embrace and drive an iterative, agile development process: push early integrations, prototype quickly, validate solutions with internal customers and early adopters, solve problems collaboratively as they arise, and continually refine your work based on real feedback. You will balance near-term impact with a bold, forward-thinking product vision that anticipates the needs of tomorrow’s marketers.
• Support, maintain, and evolve your components post-launch, responding to customer needs, monitoring real-world performance, and delivering ongoing improvements in response to user and business insight.
• Document your systems and learnings to enable efficient collaboration within the team and fast, informed future iteration.

What is required for success in this role?

• A holistic engineering mindset oriented toward product excellence and impact
• Hands-on expertise in building, testing, and shipping GenAI/LLM-based agentic systems
• Practical proficiency across software engineering, applied LLM development, and DevOps practices, ensuring real-world reliability—not just theoretical capability
• Comfort with fast-paced, iterative development and a user-validated, visionary approach to technology and business outcomes

What technologies and tools does the Autonomous Marketing team work with?

• Programming languages - Python/FastAPI on Backend, TypeScript/Angular on UI 
• AI-Agentic tech stack - Gemini, PydanticAI, OpenAI, Phoenix Arize
• Google Cloud Platform services - VertexAI, GKE, BigQuery
• Data Storage and Processing - PostgreSQL, MongoDB

Experience and Qualities We Seek

We're looking for engineers who exemplify a product-driven, hands-on mindset and are skilled at translating visionary ideas into reliable, scalable, and impactful AI solutions for production environments. The ideal candidate is passionate about building GenAI/LLM-based agentic systems that not only work in theory but deliver measurable impact for users and businesses.

Professional experience

• Hands-on experience designing, evaluating, and maintaining production-grade AI agentic systems—with a proven record of applying GenAI, LLMs, and agent orchestration in real-world scenarios.
• Proven proficiency in Python engineering and modern backend development—including data processing, API development, and creation of robust microservice architectures. Experience with prompt engineering and context/memory design for LLM-powered systems is highly valued.
• Operational knowledge across the full stack: solid grasp of software engineering principles, LLM/GenAI application development, cloud operations (especially in GCP environments), CI/CD, and DevOps practices. You know how to build, deploy, monitor, and scale complex agentic systems in production.
• Expertise in evaluation methodologies: you develop comprehensive test suites and system-level benchmarks, ensuring the functional and behavioral quality of autonomous agents and their integration into broader business workflows.
• Experience collaborating with product managers, data scientists, and UX/UI engineers to align technical solutions tightly with business goals and user needs—demonstrating a track record of delivering features that ship, iterate, and create value for customers.

Personal qualities

• Strong initiative, ownership, and an agile problem-solving approach: you thrive in fast-paced, iterative environments, embrace feedback from early adopters, and adapt solutions quickly.
• Excellent communication and collaboration skills, with a demonstrated ability to work cross-functionally in diverse teams and articulate complex technical concepts to non-technical partners.
• A commitment to excellence: you are dedicated to continuous learning, knowledge sharing, and raising the bar for both technology and product impact.
• Genuine excitement for pushing boundaries: you stay curious about emerging AI and agentic technologies, and are excited to help define the future of marketing through creative, high-impact engineering.

Excited? Join us and transform the future of commerce experiences.

Bloomreach powers digital commerce with AI-native solutions for marketing automation, search and merchandising, conversational shopping assistance, and headless content management—driven by unified customer and product data for personalization and measurable business impact. We're expanding with new ideas and modules.

For example, our Autonomous marketing solution, you can get more info about our vision here -  https://visit.bloomreach.com/innovation-fest-2025-after

Join the Engineering team working on an Autonomous marketing solution to help shape the future of autonomous marketing. As a Software Engineer, you'll build and deploy agentic AI systems with real-world impact, collaborating alongside innovators redefining how brands engage millions of customers.

For candidates at the P3 / Senior Software Engineer level, starting monthly compensation begins at 3700 € gross, with the final offer tailored for each candidate based on their skills and experience(, and location). Stock options and a comprehensive benefits package are also included.

If you're passionate about prompt and context engineering, driven by impact, and want to be a key part of defining the industry's future, Bloomreach wants to hear from you. This role focuses on solving real-world problems with production-ready agentic systems, not just internal experimentation.

What challenge awaits you?

Step into the forefront of autonomous marketing innovation. As a member of the Engineering team, you’ll take on the challenge of designing, developing, and scaling production-grade agentic AI systems that are redefining how brands connect with millions of customers in real time.

You will tackle the complexities of architecting and orchestrating powerful AI agents—leveraging the latest in large language models, prompt and context engineering, and agentic workflows—to drive automated, personalized engagement across diverse digital channels. Your work involves shaping the context and memory that empowers our agents to make smart, data-driven decisions at scale.

Collaboration is key: you’ll partner with fellow engineers, data scientists, and product leaders to integrate agentic intelligence into our platform, ensuring seamless alignment with customer data, analytics, and channel experiences. This is a unique opportunity to apply your technical expertise in prompt and context engineering, contribute to an ambitious product vision, and help define the future of the marketing industry through autonomous, AI-driven solutions.

What will you do?

• Design and deliver meaningful, production-grade features end-to-end, always anchored in clear user needs and measurable business value. You’ll translate high-level vision and customer requirements into actionable plans, robust code, and scalable solutions.
• Define technical specifications directly from business goals and work collaboratively with product managers, engineers, QAs, and data scientists to ensure that every build solves a concrete problem for users.
• Build and ship APIs and backend components that drive agentic workflows and seamless AI-powered automation—ensuring performance, security, and maintainability at scale.
• Integrate and operationalize state-of-the-art GenAI, LLMs, and orchestration frameworks so your agents take real business actions in production environments, not just in proofs-of-concept.
• Take full accountability for the robustness of your solutions: developing comprehensive test suites, rigorous evaluation frameworks (including agent- and system-level benchmarking), and monitoring strategies to ensure reliability and measurable outcomes. You'll evaluate both automated agentic behaviors and overall system performance to guarantee these systems perform as intended in live scenarios.
• Apply your full stack of skills—ranging from software engineering and prompt/context design to real-world LLM/GenAI operations and DevOps best practices. You’ll make agentic systems functional, maintainable, and resilient from dev environments through to production and post-launch.
• Embrace and drive an iterative, agile development process: push early integrations, prototype quickly, validate solutions with internal customers and early adopters, solve problems collaboratively as they arise, and continually refine your work based on real feedback. You will balance near-term impact with a bold, forward-thinking product vision that anticipates the needs of tomorrow’s marketers.
• Support, maintain, and evolve your components post-launch, responding to customer needs, monitoring real-world performance, and delivering ongoing improvements in response to user and business insight.
• Document your systems and learnings to enable efficient collaboration within the team and fast, informed future iteration.

What is required for success in this role?

• A holistic engineering mindset oriented toward product excellence and impact
• Hands-on expertise in building, testing, and shipping GenAI/LLM-based agentic systems
• Practical proficiency across software engineering, applied LLM development, and DevOps practices, ensuring real-world reliability—not just theoretical capability
• Comfort with fast-paced, iterative development and a user-validated, visionary approach to technology and business outcomes

What technologies and tools does the Autonomous Marketing team work with?

• Programming languages - Python/FastAPI on Backend, TypeScript/Angular on UI 
• AI-Agentic tech stack - Gemini, PydanticAI, OpenAI, Phoenix Arize
• Google Cloud Platform services - VertexAI, GKE, BigQuery
• Data Storage and Processing - PostgreSQL, MongoDB

Experience and Qualities We Seek

We're looking for engineers who exemplify a product-driven, hands-on mindset and are skilled at translating visionary ideas into reliable, scalable, and impactful AI solutions for production environments. The ideal candidate is passionate about building GenAI/LLM-based agentic systems that not only work in theory but deliver measurable impact for users and businesses.

Professional experience

• Hands-on experience designing, evaluating, and maintaining production-grade AI agentic systems—with a proven record of applying GenAI, LLMs, and agent orchestration in real-world scenarios.
• Proven proficiency in Python engineering and modern backend development—including data processing, API development, and creation of robust microservice architectures. Experience with prompt engineering and context/memory design for LLM-powered systems is highly valued.
• Operational knowledge across the full stack: solid grasp of software engineering principles, LLM/GenAI application development, cloud operations (especially in GCP environments), CI/CD, and DevOps practices. You know how to build, deploy, monitor, and scale complex agentic systems in production.
• Expertise in evaluation methodologies: you develop comprehensive test suites and system-level benchmarks, ensuring the functional and behavioral quality of autonomous agents and their integration into broader business workflows.
• Experience collaborating with product managers, data scientists, and UX/UI engineers to align technical solutions tightly with business goals and user needs—demonstrating a track record of delivering features that ship, iterate, and create value for customers.

Personal qualities

• Strong initiative, ownership, and an agile problem-solving approach: you thrive in fast-paced, iterative environments, embrace feedback from early adopters, and adapt solutions quickly.
• Excellent communication and collaboration skills, with a demonstrated ability to work cross-functionally in diverse teams and articulate complex technical concepts to non-technical partners.
• A commitment to excellence: you are dedicated to continuous learning, knowledge sharing, and raising the bar for both technology and product impact.
• Genuine excitement for pushing boundaries: you stay curious about emerging AI and agentic technologies, and are excited to help define the future of marketing through creative, high-impact engineering.

Excited? Join us and transform the future of commerce experiences.

About the Role

We're looking for a curious, technically-minded problem solver — not someone to just close tickets.

You'll troubleshoot complex customer issues across voice, messaging, APIs, IoT, and AI products, digging into networking problems, debugging integrations, and analysing logs alongside engineering teams. But this role goes further: we're building an AI-first support model, and as you develop product expertise, you'll help shape it — building bots, automating workflows, and turning repetitive tasks into cron jobs. If you've ever spotted a repetitive task and actually built the fix for it, you'll fit right in. A background in software engineering, networking, or a related technical field (however you got there) is ideal — We care about what you can do, not where you learned it.

What You'll Do

• Troubleshoot: complex customer issues across networking, APIs, and communications products
• Investigate: using tools like Postman, cURL, Wireshark, Linux terminal and our internal tooling
• Collaborate: with customers, vendors, and engineering teams to resolve cases
• Automate: contribute to bot-building and workflow automation
• Document: solutions and improve self-service resources
• Learn: VoIP protocols, internal systems, and new technologies as the role evolves

Your Toolkit

• Troubleshooting: Postman, cURL, Wireshark, sngrep, Linux terminal
• Ticketing and Comms: Zendesk, Slack
• Collaboration: Google Workspace (Gmail, Calendar, Docs, Sheets, Meet)
• Automation: n8n, Zapier, OpenClaw (internal AI platform), scripting (Python, Bash, etc.)
• Version Control: GitHub
• Analytics: Metabase, Graylog, Jira

What We're Looking For

Must-Have

• Background in Computer Science, IT, networking, or equivalent hands-on experience
• Networking fundamentals: solid understanding of how the internet works, including DNS, routing, IP addressing, and HTTP/HTTPS
• API experience: comfortable with REST APIs, webhooks, and tools like Postman or cURL
• Linux terminal proficiency: comfortable navigating filesystems, reading logs, and running commands
• Problem-solving mindset: you dig into issues, ask good questions, and don't give up easily
• Communication skills: you'll need to be highly proficient in English, both written and verbal - owning customer communication and technical documentation from day one

Nice-to-Have

• Familiarity with scripting or programming (Python, Bash, JavaScript, or similar)
• Understanding of AI concepts such as RAG, MCPs, embeddings, and prompt engineering
• Experience using n8n, Zapier, Git/GitHub, or similar

You don’t need to tick every box -  if you’re keen to learn that's the box that matters most ! 

This role operates on Central Time (UTC-6), 9am–6pm Monday to Friday