All active TypeScript roles based in Latvia.
Pick a job to read the details
Tap any role on the left — its description and apply link will open here.
Share this job
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:
What success looks like (after 6 months):
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
Ready to apply?
Apply to Cast AI
Share this job
Point Wild helps customers monitor, manage, and protect against the risks associated with their identities and personal information in a digital world. Backed by WndrCo, Warburg Pincus and General Catalyst, Point Wild is dedicated to creating the world’s most comprehensive portfolio of industry-leading cybersecurity solutions. Our vision is to become THE go-to resource for every cyber protection need individuals may face - today and in the future.
Join us for the ride!
About the Role:
We’re looking for a Backend Engineer to contribute to a next-generation security initiative. You’ll be part of a small, highly technical team working on novel approaches to secure systems - with a focus on cryptography, automation, and AI-powered analysis. You’ll work closely with senior engineers and contribute hands-on to the codebase across the stack. This role involves hands-on development, learning opportunities, and collaboration across engineering, product, and design.
Day to Day:
What you bring to the table:
Extra Credit:
As part of Point Wild, you will:
Solve real customer problems. Point Wild’s point solutions allow consumers to address their immediate cyber protection needs. Our mandate is to continuously anticipate our customers’ evolving digital security needs to create best-in-class solutions aimed at keeping them safe.
See your impact. We are a scrappy, nimble organization where individual contributions are needed and valued. You will see your impact every day.
Accelerate your career. As we expand, you will have the opportunity to learn new technologies, products, and markets in a fast-paced, growth-oriented environment.
Most importantly, you’ll get to work with other talented people at a company where people matter. If you want to put your fingerprint on an organization and leapfrog your growth, this is the place for you.
In keeping with our beliefs and goals, no employee or applicant will face discrimination or harassment based on race, color, ancestry, national origin, religion, age, gender, marital domestic partner status, sexual orientation, gender identity, disability status, or veteran status. Above and beyond discrimination or harassment based on “protected categories,” Point Wild is committed to being an inclusive community where all feel welcome. Whether blatant or hidden, barriers to success have no place at Point Wild.
Important privacy information for United States based job applicants can be found here.
Ready to apply?
Apply to Point Wild
The mission of Speechify is to make sure that reading is never a barrier to learning.
Over 50 million people use Speechify’s text-to-speech products to turn whatever they’re reading – PDFs, books, Google Docs, news articles, websites – into audio, so they can read faster, read more, and remember more. Speechify’s text-to-speech reading products include its iOS app, Android App, Mac App, Chrome Extension, and Web App. Google recently named Speechify the Chrome Extension of the Year and Apple named Speechify its 2025 Design Award winner for Inclusivity.
Today, nearly 200 people around the globe work on Speechify in a 100% distributed setting – Speechify has no office. These include frontend and backend engineers, AI research scientists, and others from Amazon, Microsoft, and Google, leading PhD programs like Stanford, high growth startups like Stripe, Vercel, Bolt, and many founders of their own companies.
Overview
The responsibilities of our Platform team include building and maintaining all backend services, including, but not limited to, payments, analytics, subscriptions, new products, text to speech, and external APIs.
This is a key role and ideal for someone who thinks strategically, enjoys fast-paced environments, is passionate about making product decisions, and has experience building great user experiences that delight users.
We are a flat organization that allows anyone to become a leader by showing excellent technical skills and delivering results consistently and fast. Work ethic, solid communication skills, and obsession with winning are paramount.
Our interview process involves several technical interviews and we aim to complete them within 1 week.
What You’ll Do
An Ideal Candidate Should Have
What We Offer
Think you’re a good fit for this job?
Tell us more about yourself and why you're interested in the role when you apply.
And don’t forget to include links to your portfolio and LinkedIn.
Not looking but know someone who would make a great fit?
Refer them!
Speechify is committed to a diverse and inclusive workplace.
Speechify does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status.
Ready to apply?
Apply to Speechify
Cookies & analytics
This site uses cookies from third-party services to deliver its features and to analyze traffic.