SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 189,000 - 231,000 / annual
EarnIn is seeking an AI Builder to make AI-native engineering a core capability across the organization. This is not a traditional software engineer role with AI as a side project—you'll be hired as an AI builder who also writes great software, fundamentally rethinking how the company designs, builds, tests, and ships products.
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 enable safe, fast, and durable AI adoption across teams.
Key responsibilities include:
**Agents in Production**: Design agent architectures including prompts, reasoning chains, tool calls, MCP servers, agent scaffolding, context harnesses, and a Skills Marketplace. You're building production infrastructure that every squad at EarnIn will build on—not proofs of concept.
**Reimagined Product Development Lifecycle**: Challenge and rethink each stage of the PDLC from scoping and design through review, testing, deployment, and monitoring. Replace manual friction with agentic workflows. Build evaluation pipelines, automated PR hygiene, deployment gating, and generation-to-merge metrics that make governed AI fast rather than slow.
**Evaluation Infrastructure**: Own the evaluation infrastructure—building pipelines, benchmarks, and quality gates that determine whether AI is working, degrading, or ready to ship. Design eval harnesses for AI-assisted workflows, set baselines for generation-to-merge and review latency, and make model quality visible and trustworthy across teams.
**Production-Ready Patterns**: Take engineering experiments that work and turn them into reusable libraries, templates, and reference implementations. Enable squads to fork and ship AI integrations in a week without solving the same problem twice.
Success means teams ship AI-assisted features faster with fewer rework loops, your harnesses are actively used and well-documented, and AI pilot quality and safety metrics are visible, trustworthy, and improving.
You'll have 3+ years of full-time software engineering experience with at least 2 years building tooling, platforms, or internal developer products. You need hands-on experience with LLM integration patterns (prompt engineering, RAG, tool calling, agent architectures), proficiency across the stack, and experience with orchestration frameworks like MCP or LangChain. Strong opinions about developer experience and a track record of building things other engineers actually use are essential.
You'll stand out with hands-on reinforcement learning experience (RLHF, RLAIF, reward modeling), fintech or regulated environment background, and AI governance work (bias evaluation, audit logging, model cards).
