AI Lead Engineer

About the role

We are looking for an AI Lead Engineer to drive the technical strategy and delivery of AI-powered solutions across client projects and internal initiatives. You will own end-to-end execution: from discovery and solution design to implementation, deployment, and continuous improvement.

This is a hands-on leadership role: you will architect, build, and mentor, while collaborating closely with Delivery, Product/PM, and Engineering leadership.

What you’ll do

• Lead AI solution design for client projects (LLM apps, RAG, assistants, automation, analytics/ML features).
• Own technical architecture: model selection, prompting, RAG pipelines, evaluation, observability, performance, scalability.
• Build production-grade AI services (APIs, background workers, integrations) and ensure quality, reliability, and security.
• Define best practices: coding standards, reusable components, templates, and reference architectures.
• Establish evaluation & QA practices for AI outputs (offline evaluation sets, automated tests, human review flows).
• Drive cross-functional alignment with PM/BA and stakeholders; translate business needs into technical scope and milestones.
• Mentor engineers, run technical reviews, and help grow AI competency across the organization.
• Support presales: effort estimation, technical discovery, solution outlines, and risk/assumption management.

Requirements

• 5+ years of software engineering experience, with 2+ years building AI/LLM-enabled products (or equivalent depth).
• Strong experience with Python (preferred) and/or TypeScript/Node.js in production systems.
• Solid understanding of:
  • LLM application patterns: RAG, tool/function calling, agents/workflows, prompt engineering
  • Embeddings, vector databases, retrieval strategies, reranking
  • Model performance, cost optimization, latency management
• Experience building APIs and services (REST/GraphQL), background jobs, integrations with external systems.
• Hands-on experience with cloud deployment (AWS/Azure/GCP) and modern DevOps practices (CI/CD, containers).
• Ability to lead technical decisions, communicate trade-offs, and manage delivery risks.
• Strong written and spoken English (client-facing communication).

Nice to have

• Experience with evaluation frameworks (e.g., custom eval harnesses, golden datasets, automated regression tests).
• Fine-tuning / adapters, classical ML pipelines, MLOps tooling.
• Experience with privacy/security constraints (PII handling, access control, audit trails).
• Prior experience in outsourcing/consulting environments with multiple parallel clients.

Typical tech stack (flexible)

• LLM providers: OpenAI / Azure OpenAI / Anthropic / open-source (as needed)
• Frameworks: LangChain / LangGraph / LlamaIndex (or custom pipelines)
• Vector DB: Pinecone / Weaviate / Qdrant / pgvector
• Backend: Python (FastAPI) and/or Node.js (NestJS)
• Data: Postgres, Redis, object storage
• Infra: Docker, Terraform (optional), GitHub Actions, Kubernetes (optional)
• Observability: OpenTelemetry, Prometheus/Grafana, Sentry; LLM tracing tools when relevant

What success looks like (first 3–6 months)

• You ship at least 1–2 AI solutions into production with measurable value (quality, latency, cost).
• You establish a repeatable blueprint for AI projects (architecture + evaluation + deployment checklist).
• The team has clear standards for building and testing AI features, and delivery predictability improves.

Working conditions

• Remote-friendly (Europe time zone preferred; partial overlap required).
• Project-base engagement.
• Opportunity to influence architecture, team practices, and the AI roadmap.