AI Engineer

TL;DR

AI Engineer (LLM): Design, build, and deploy production-grade AI systems powered by large language models with an accent on multi-agent orchestration, RAG pipelines, vector databases, and agentic frameworks. Focus on creating evaluation frameworks, implementing feedback loops, optimizing prompts for latency/cost/quality, and ensuring reliable outputs at scale.

Location: Lisbon

Company

Global AI-native consultancy trusted by leading enterprises to deliver AI into production across Financial Services, Energy & Utilities, Healthcare, Retail & CPG, and Manufacturing.

What you will do

• Design and implement production AI systems integrating LLMs, RAG pipelines, vector databases, and agentic frameworks.
• Create evaluation frameworks to measure and monitor system performance, accuracy, and reliability.
• Build and maintain production-grade AI applications with clean code, error handling, APIs, and data pipelines.
• Implement retrieval systems including vector/graph databases, ingestion pipelines, and techniques like HyDE.
• Implement feedback loops and observability to continuously improve system performance.
• Craft effective prompts and optimize for latency, cost, and quality across model providers.

Requirements

• Hands-on experience building applications with LLM APIs and deep understanding of their capabilities, limitations, and failure modes.
• Practical implementation of RAG architectures, vector databases, knowledge graphs, and prompt engineering.
• Experience building multi-step LLM workflows and agentic systems using frameworks like LangGraph or custom implementations.
• Strong Python proficiency with production API/service development and cloud platform knowledge (AWS, GCP, Azure).
• Understanding of distributed systems, CI/CD, testing, deployment pipelines, and cloud-native infrastructure.
• Strong data manipulation skills (pandas, SQL) and evaluation strategies for LLM-based systems.
• Ability to work with ambiguity, optimize non-deterministic systems through experimentation, balancing latency/cost/quality.

Nice to have

• Experience with AI-assisted coding tools like Claude Code, OpenAI Codex, GitHub Copilot.
• Experience with fine-tuning LLMs, real-time streaming, multimodal models, or Elasticsearch.
• Familiarity with model observability tools (LangSmith, Weights & Biases) and cost optimization.
• Experience in specialized verticals like financial services, energy, healthcare with compliance and security practices.
• Experience with tool calling agents, handoffs, and guardrails.

Culture & Benefits

• Fast-growing startup with career growth opportunities and collaborative environment.
• 25 days holiday plus bank holidays, pension scheme, discretionary company and personal bonuses.
• €1,500 training budget + 5 training days, choose your own gear (MacBooks, PCs, accessories).
• Social events including squad meets, summer/Christmas events.