Senior AI Engineer

Location: Remote; applicants may be located in Ukraine, Bosnia, the European Union, Georgia, North Macedonia, Serbia, or Turkey, and must be within approximately ±4 hours of CET.

Company

hirify.global creates and operates consumer subscription products across health, education, and entertainment.

What you will do

• Own the AI layer of a core D2C subscription product from initial experiments through live production, including prompt systems, structured outputs, evaluation, observability, and model selection.
• Design dynamic prompts with conditional logic and context injection, enforce predictable JSON and function-calling outputs, and build LLM workflows with LangChain, LlamaIndex, or custom systems.
• Build reliable Browserbase Functions and Playwright automations, classify screens with models, determine which steps use models or deterministic code, and ship versioned, reproducible workers.
• Orchestrate runs through Hatchet with retries, timeouts, and failure traces; manage rate limits, fallbacks, model costs, and production incidents.
• Build evaluation pipelines with test datasets, LLM-as-a-judge systems, RAGAS-style metrics, and Langfuse scoring and tracing.
• Run quantitative A/B experiments across models and prompts, re-evaluate emerging architectures, fine-tune when required, and remain accountable for released AI features.

Requirements

• 5+ years of software engineering experience with Node.js, TypeScript, Next.js, and Postgres, including edge or serverless runtimes such as Cloudflare Workers.
• Production browser automation experience with Playwright and Browserbase or a similar platform, including resilient selectors, retries, and large-scale failure handling.
• Production experience with dynamic prompting using input variables and injected context.
• Production experience with structured outputs, including JSON mode, function calling, and Zod or JSON schemas.
• Experience with unified LLM APIs or AI gateways such as OpenRouter or Cloudflare AI Gateway, including rate limits, fallbacks, and cost-effective model selection.
• Experience with LLM observability using Langfuse or a similar tool, including tracing, test datasets, and scoring integration.
• Experience developing evaluation methodologies with RAGAS or custom LLM-as-a-judge systems.
• Ability to make decisions from benchmarks and trace data, convert generation logs into actionable metrics, build feedback loops, validate LLM output before trusting it, and own outcomes through and after production release.

Culture & Benefits

• Remote work environment with flexibility to work from anywhere subject to the CET time-zone requirement.
• Unlimited paid time off and paid national holidays.
• Company-provided MacBook for employees who need one.
• Flexible independent contractor agreement offering autonomy and contractor flexibility.
• Fast-growing environment focused on ambitious, high-impact work and continuous professional growth.

Hiring process

• Application review typically takes 3–5 days, though it may take longer depending on application volume.
• Recruiter screening lasting 40 minutes.
• Technical interview lasting 60 minutes, followed by a 30-minute final interview.