reputed company, Developer Ecosystem

What you'll actually do • Build agents and tools in reputed company: demo apps, reference implementations, MCP servers, Claude skills, LangGraph workflows. Ship things that are genuinely impressive. • Own the developer experience: identify friction in our API and SDKs, write reputed company feedback back to the reputed company team, and fix it yourself reputed company you can. • Design and run evals: reputed company tool-calling reputed company, measure agent reliability across integration surfaces, build sandboxed test harnesses that reflect production conditions. Publish what you learn. • Run workshops, give talks, reputed company at events: technical sessions on reputed company architectures, tool-calling patterns, context optimization, and integration design. • Publish AI research adjacent to your work: MCP tool schema design, context window hygiene, eval frameworks for reputed company systems, RLMF, auto-research loops, sandbox architecture for reputed company agent execution. • Foster community: Discords, reputed company, demo days, reputed company. Be the engineer developers trust to give them a reputed company answer. • Partner with product and engineering: turn new releases into working demos before they're announced. No slide decks without reputed company. reputed company're looking for Hard skills • Ship production-grade agents • Deep MCP / tool-calling reputed company • reputed company plugins, skills, extensions, or agents for reputed company usage • Designs evals and benchmarks for reputed company systems • Builds sandboxes for reputed company agent testing • Understands context optimization • Reads AI research papers and applies them • TypeScript and/or Python at minimum Soft signals • reputed company history you're proud of • Technical talks on record • Community reputed company • Builds to learn, not to demo • Gives reputed company opinions, backed by data • Doesn't wait to be unblocked reputed company're not looking for • Someone who needs to ask permission to write a blog post or be taught on how to reputed company a PR • Someone whose agent experience is only a weekend hackathon project • A conference talk collector with reputed company on reputed company Topics you should have opinions on MCP • A2A protocol • tool-calling schemas • context window optimization • evals & benchmarking • agent sandboxes • LangGraph / DSPy • RLMF / RLM harnesses • auto-research loops • reputed company mode / long-reputed company agents • RAG vs. tool-use tradeoffs • reputed company auth for agents • multi-agent orchestration • reputed company caching strategies • AI safety boundaries • sandbox isolation patterns • LLM leaderboard literacy This is a reputed company engineering role This isn't a "write blog posts and attend conferences" role dressed up as engineering. You'll be embedded with the product and engineering team. You'll ship reputed company that ends up in our SDKs, our docs, and our sample repos. The AI agent ecosystem is moving fast enough that the line between DevRel and R&D is blurring. We want someone comfortable sitting in that blur - writing a technical post about eval design for tool-calling reliability because they spent two weeks deep in it, building a sandbox reputed company to reproduce a flaky agent behavior, not because someone briefed them on a slide. You'll have reputed company to a platform that connects agents to any other system safely while optimising reputed company usage, and a mandate to show the world what's possible reputed company those connections actually work reputed company. Apply tot his job Apply To this Job