Senior AI & LLM Engineer

100% Remote (Worldwide)

Note: the first 3 - 6 months will require you to work as a freelancer and issue monthly invoices.

You will be the 3rd member of the team, working with the co-founders and have a big influence on crafting what the product and company becomes.

For the right person we are willing to offer full-time employment and meaningful equity after the initial 3 - 6 month trial period.

Full time - 40 hours p/week

Note: if you can only commit to 30 but feel like the role is good match, please apply

€4000 - €5500 p/month (depends on experience, skill and commitment)

You can be located anywhere in the world

It's important that you genuinely enjoy what you do and take pride in your output.

You will need to balance engineering integrity with speed. Previous start-up experience is preferred.

Core Stack Proficiency

• TypeScript — primary language across the entire stack; strong typing, Zod schema validation, and generics
• Next.js 15 (App Router, Server Components, Server Actions, Route Handlers) — the frontend and API layer

Interested in remote work opportunities in Development & Programming? Discover Development & Programming Remote Jobs featuring exclusive positions from top companies that offer flexible work arrangements.

• NestJS — modular backend architecture with decorators, guards, middleware, cron jobs, and dependency injection
• React 19 — modern component patterns, context providers, hooks
• Prisma ORM — schema design, migrations, and query optimization against PostgreSQL
• Tailwind CSS v4 — utility-first styling, responsive design, theming (white-label/multi-tenant branding)

AI & LLM Engineering (Primary Emphasis)

• Multi-provider LLM integration — hands-on experience with OpenAI, Anthropic Claude, and Google Gemini APIs, including streaming, structured outputs, and tool/function calling
• Prompt engineering — designing robust, role-based prompts for extraction, synthesis, analysis, and generation tasks; few-shot patterns; schema-constrained output
• Agentic workflows — building multi-step, LLM-driven pipelines where models call tools, process results, and loop autonomously (job queues that orchestrate scraping → LLM analysis → report generation)
• RAG patterns — document ingestion (PDF, DOCX, XLSX), text extraction, and contextual retrieval for conversational AI
• AI-powered product features — chat interfaces, document Q&A, automated chart/report generation, sentiment analysis, persona generation, alignment scoring

Data Pipeline & Automation

• Web scraping orchestration — experience with services like Apify, proxy management (Oxylabs), and headless browsers (Puppeteer)
• Job queue design — async processing pipelines with status tracking, error handling, and retry logic
• Cron-based scheduling — background task orchestration
• Data transformation — taking raw scraped data through LLM-powered extraction into structured, actionable outputs

Infrastructure & DevOps (AWS-First)

• AWS EKS — deploying, scaling, and managing containerized services on Kubernetes; pod configuration, health checks, autoscaling, service mesh basics
• Terraform — infrastructure-as-code for provisioning and managing AWS resources (VPCs, EKS clusters, RDS, S3, IAM, ALBs, security groups); module design, state management, and CI-driven plan/apply workflows

Browse our curated collection of remote jobs across all categories and industries, featuring positions from top companies worldwide.

• Docker — writing production-grade Dockerfiles, multi-stage builds, container orchestration
• AWS Services — hands-on experience with:
• RDS (PostgreSQL) — managed database, connection pooling, backups, read replicas
• S3 — object storage for assets, documents, and generated reports
• ECR — container registry for EKS deployments
• IAM — least-privilege roles, service accounts, OIDC for Kubernetes
• ALB / Ingress — load balancing, TLS termination, routing
• CloudWatch / CloudTrail — logging, monitoring, alerting
• Secrets Manager or SSM Parameter Store — secure credential management
• SES or integration with Resend — transactional email
• Cognito or self-managed JWT auth — replacing managed auth with custom JWT/JWKS validation on EKS
• CI/CD — GitHub Actions or similar pipelines for building images, running Terraform, and deploying to EKS (blue/green or rolling deployments)
• Helm — templating Kubernetes manifests for environment-specific deployments

What Sets a Great Candidate Apart

• Has built production systems where LLMs are core infrastructure, not just a chat widget — e.g., pipelines that rely on structured extraction, multi-model routing, or tool-use loops
• Can design agentic architectures end-to-end: defining tools, managing conversation state, handling failures in multi-step LLM workflows
• Understands the tradeoffs between LLM providers (cost, latency, capability) and can implement provider-agnostic abstractions
• Has migrated services from managed platforms (Supabase, Vercel) to self-hosted AWS infrastructure — understands what you lose (convenience) and what you gain (control, cost predictability)
• Experience with multi-tenant SaaS patterns (org-scoped data, white-labeling, RBAC)
• Comfortable working across the full stack — from Prisma schema design to React UI to Terraform modules — in a single sprint
• Uses AI-assisted development tools (Claude Code, Copilot, Cursor) fluently as part of their daily workflow