SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 228,000 - 279,000 / annual
EarnIn is building AI-native engineering as a core capability across the organization. This role is for an AI builder who writes great software and thinks about how to apply AI agents to every step of the product development lifecycle—from design and testing through deployment and monitoring.
You'll work at the intersection of platform engineering, developer experience, and applied AI, partnering with architects, domain leads, and product engineers to build the tools, patterns, and guardrails that make AI adoption fast, safe, and durable.
Key responsibilities:
• Design agent architectures and reasoning chains. You'll build production infrastructure including MCP servers, agent scaffolding, context harnesses, and a Skills Marketplace that every squad at EarnIn builds on top of.
• Rethink the product development lifecycle. Challenge each stage—from scoping and design through review, testing, deployment, and monitoring—and replace manual friction with agentic workflows. Build evaluation pipelines, automated PR hygiene, deployment gating, and generation-to-merge metrics.
• Own evaluation infrastructure. Design eval harnesses for AI-assisted workflows, set generation-to-merge and review latency baselines, and make model quality visible and trustworthy across teams. Build pipelines and benchmarks that tell you whether AI is working, degrading, or ready to ship.
• Graduate pilots to production. Take what's working in engineering experiments and turn it into reusable libraries, templates, and reference implementations that other squads can fork and ship in a week. Build things the next team can rely on, not just interesting prototypes.
Success means teams across engineering can ship AI-assisted features faster with fewer rework loops, the harnesses you build are actively used and well-documented, and AI pilot quality and safety metrics are visible, trustworthy, and improving.
Requirements:
• 4+ years of full-time software engineering experience, with at least 2 years building tooling, platforms, or internal developer products
• Bachelor's, Master's, or PhD in Computer Science, Computer Engineering, or related technical discipline (or equivalent industry experience)
• Hands-on experience with LLM integration patterns: prompt engineering, RAG pipelines, tool/function calling, and agent architectures
• Proficiency working across the stack when needed
• Experience with MCP, LangChain, or comparable orchestration frameworks
• Experience with open source LLM models
• Strong opinions about developer experience and track record of building things other engineers actually use
You'll stand out if you have:
• Hands-on experience with reinforcement learning (RLHF, RLAIF, or reward modeling in applied product contexts)
• Experience in fintech or regulated/security-sensitive environments
• Hands-on work with AI governance (bias evaluation, audit logging, model cards)
• Exposure to multi-step reasoning pipelines or human-in-the-loop system design
