Our client is the global leader in regulatory and sustainability intelligence, helping the world's largest companies navigate Environment, Health & Safety, Corporate Sustainability, and Product Compliance.

They are reinforcing their AI capabilities to keep their leadership as an AI-native compliance intelligence platform, with a foundational AI platform built around ontology, data, and platform surfaces, strong CAIO sponsorship, and direct executive air cover for the AI transformation.

This is the builder seat on that team. You will ship the AI product features themselves: the LLM-powered services, retrieval workflows, and agentic capabilities that turn the platform into products clients rely on. You will report to the Engineering Team Manager of the AI team and work alongside platform, data, and ontology specialists who own the infrastructure you build on top of.

🚀 Responsibilities:

AI Feature Delivery

• Build, ship, and own LLM-powered features and AI microservices in Python, from prototype to production-grade containerized services.

• Implement RAG and agentic workflows: retrieval, prompt orchestration, tool / function calling, and the glue that turns models into real product capability.

Prompts, Evals & Guardrails

• Design and iterate on prompts, build eval sets, and wire in runtime guardrails so features behave predictably on real regulatory content.

• Integrate multi-provider LLMs (OpenAI, Anthropic, Google) through the platform's gateway, reasoning about cost, latency, and quality trade-offs.

Building on the Platform & Data Layers

• Work as a fast, fluent consumer of the AI Data Vault (vector DB, retrieval surface) and the AI platform (gateway, prompt registry, agent runtime), owned by the platform and data leads.

• Wire features into SQL stores, message brokers (Kafka), and search (Elasticsearch) as the work requires.

Quality & Operability

• Write tested, observable code and instrument what you ship: latency, cost, token usage, and traces (Splunk, OpenTelemetry) so features can be operated, not just deployed.

• Participate actively in code review, debug production issues, and prototype rapidly with AI coding assistants before hardening for scale.

👤 Profile sought:

Experience

• 3 to 5 years of hands-on software engineering, with a track record of shipping production services that real users depend on.

• Direct experience integrating LLMs into products (RAG, prompt engineering, agentic / tool-use patterns), beyond notebook prototypes.

• Comfortable owning a feature end-to-end: design, build, test, deploy, and operate.

Technical skills

• Strong Python skills: clean, tested, production-grade code.

• Hands-on LLM application work: RAG pipelines, prompt orchestration, function calling or agent frameworks, and the basics of evals and guardrails.

• Solid SQL fundamentals and comfort consuming vector databases (Qdrant, Pinecone, pgvector, or similar). Operator-level depth is a plus, not a requirement.

• Production experience with a cloud platform (Azure preferred, AWS or GCP a plus), containerized deployment, and CI/CD (Bitbucket Pipelines, GitHub Actions, Azure DevOps, or equivalents).

• Daily-driver Linux comfort: shell, process management, basic troubleshooting.

• Active user of AI coding assistants, integrated into your daily workflow.

Bonus

• Experience with agent frameworks, MCP servers, or comparable tool-use / function-calling surfaces.

• Familiarity with Kafka or equivalent message brokers, and Elasticsearch / OpenSearch.

• Background in NLP, information extraction, or document understanding.

• Experience with MLflow or experiment tracking.

• Experience in regulated industries (EHS, legal, financial, healthcare).

• Contributions to open-source LLM, agent, or retrieval tooling.

Languages

• Fluent English required.

Soft skills

• Bias for delivery and operational discipline over research polish.

• Opinionated about tools, pragmatic about deadlines.

• Strong communicator who works well with leads, product, and reviewers.

• Eager to grow: takes feedback and mentorship from senior engineers and the Engineering Team Manager.

🌍 Benefits & Culture:

• Tech stack: Azure / AKS, Terraform or Bicep, Kubernetes, Python, LLM gateways, MCP, agent frameworks, MLflow, Splunk, OpenTelemetry, Qdrant, Kafka, Elasticsearch.

• Build AI product features that ship to the world's largest companies at global scale.

• A seat on a small, high-impact AI team with strong CAIO sponsorship: short feedback loops and real influence on what you build.

• Mentorship from senior engineers and leads across platform, data, and ontology.

• Culture that treats AI tools as force multipliers, not novelties.

• Competitive compensation, benefits, and flexibility.

• Hybrid in Lisbon's office role (3 days a week at the office).

💼 Department: AI & Engineering

📍 Location: Lisbon (Hybrid)

📆 Start date: ASAP