AI Engineer

AIApply is hiring a remote AI Engineer to design, build and ship production LLM applications used by hundreds of thousands of job seekers every month. You will own end-to-end AI features: retrieval-augmented generation (RAG) pipelines, agentic workflows, model evaluation harnesses, prompt orchestration, and the serving infrastructure behind them. This is a hands-on engineering role at a fast-moving, product-led AI company. You will work directly with the founders and product team, ship to production weekly, and see your work in front of real users within days rather than quarters. We care about measurable model quality, latency and cost — not demos. We are fully remote and hire across US and European time zones.

Responsibilities Design and ship production LLM features: RAG pipelines, tool-calling agents, structured output extraction and multi-step workflows. Build and maintain evaluation harnesses — golden datasets, offline evals, LLM-as-judge scoring and regression gates in CI — so model quality is measured, not guessed. Own prompt engineering and model routing across OpenAI, Anthropic, Google and open-weight models, optimising for quality, latency and cost per request. Implement vector search and embedding pipelines (pgvector, chunking, hybrid retrieval, re-ranking) over resumes, job descriptions and user documents. Build resilient serving infrastructure: streaming responses, retries, timeouts, fallbacks, caching, rate limiting and observability. Partner with product and design to turn ambiguous ideas into shipped features, and instrument them so we know whether they worked. Review code, raise the engineering bar, and mentor teammates on applied AI practices.

Qualifications 3+ years of professional software engineering experience, with at least 1 year building production applications on top of large language models. Strong TypeScript, Python or both. Comfortable across the stack: APIs, queues, databases and cloud deployment. Practical experience with RAG, embeddings and vector databases, and a clear understanding of when retrieval helps and when fine-tuning or prompting is the better tool. Experience evaluating LLM output systematically — you have built or used eval sets, not just eyeballed results. Familiarity with the modern AI tooling ecosystem: OpenAI/Anthropic SDKs, LangChain or equivalent, function calling, streaming and structured outputs. Product sense and strong written communication — we are remote and async first. Nice to have: fine-tuning or LoRA experience, inference optimisation, Postgres/pgvector at scale, or prior work at an early-stage startup. Required Must-haves: 3+ years software engineering, hands-on production LLM work, strong Python or TypeScript, experience with RAG and embeddings, and demonstrable ownership of a shipped AI feature. Ability to overlap at least 4 hours daily with US Eastern or Central European time. Skills Large Language Models (LLMs) Retrieval-Augmented Generation (RAG) Python TypeScript Vector databases and pgvector Prompt engineering LLM evaluation and observability OpenAI and Anthropic APIs AI agents and tool calling Cloud infrastructure (AWS/GCP/Cloudflare)

Benefits Fully remote — work from anywhere Competitive salary plus meaningful equity Flexible hours and async-first culture Annual learning and AI tooling budget Home office and equipment stipend Generous paid time off Direct access to founders and real product ownership