19 Nov
|
Arcfront
|
Bengaluru
19 Nov
Arcfront
Bengaluru
About Arcfront Arcfront is a research-and-data partner to the labs building frontier models. We build RL environments, proprietary data and evals that find where a model lags and help it hill-climb. We work with several of the leading frontier labs and a growing set of neo-labs, and we are growing fast. We believe that models need to get better on real world work, and real world breakthroughs. Interestingly, most of that work is present in some shape and form inside companies. As long as we can fish that out in a way where we can make that information useful, we can be a strong enabler to the world getting better intelligence models. We are a team of researchers and engineers passionate about moving the world forward. The role You'll build the systems that turn real expert work into data and environments frontier models can learn from. This is end-to-end engineering: you take a messy, real-world workflow and turn it into something a model can be trained on, measured against and improved with.
What you'll do
• Build RL environments that simulate real software, tools and multi-step workflows, so models can practise long-horizon tasks.
• Build evaluation harnesses and the infrastructure to run them at scale: sandboxes, graders, experiment tooling and GPU/inference infra.
• Build agentic and computer-use task pipelines: single-app and multi-app environments where today's models fail.
• Build internal platforms that let domain experts create, review and validate tasks, rubrics and data quickly.
• Automate everything that doesn't need a human, so the people on each project spend their time on judgment, not busywork.
• Move fast: new models ship every few weeks, and each iteration of our data should show up as real improvement. What we're looking for
• Robust software engineering fundamentals: data structures, algorithms and clean, tested code.
• Hands-on experience building with LLMs: prompting, tool calling, agents, and knowing where they break.
• Comfort owning work end to end, from a vague problem to a shipped system.
• Attention to detail: you can move fast without shipping buggy work, and you care about corner cases.
• Strong ownership: you drive things to completion yourself. Nice to have
• Experience with RL environments, evals, benchmarks or agent frameworks.
• Competitive programming, open-source contributions, or a project where you built something real with models.
📌 Member of Technical Staff (Bengaluru)
🏢 Arcfront
📍 Bengaluru