16 days ago
Porto, PortugalSenior
Responsibilities
- Stabilize, mature, and evolve the AI platform supporting production LLM, RAG, and agent-based solutions.
- Implement guardrails, access controls, authentication, rate limiting, quotas, token management, cost monitoring, and policy enforcement.
- Support shared AI platform services such as LLM gateways, model routing, vector search, and orchestration.
- Improve deployment automation, observability, versioning, rollback, CI/CD, and production-readiness practices for AI workloads.
- Work with DevOps and platform engineering teams to deploy and operate AI services across cloud and Kubernetes environments.
- Design, build, and maintain Generative AI solutions, including RAG pipelines, agent workflows, backend APIs, and reusable services.
- Diagnose production issues and contribute to technical standards for secure, reliable, and maintainable AI systems.
- Influence technical decisions and support the development of other engineers.
Requirements
- Strong experience in AI engineering, backend engineering, platform engineering, or ML platform roles.
- Strong Python skills and experience building production-grade APIs, backend services, and integrations.
- Hands-on experience developing or operating production Generative AI solutions using cloud-hosted or open-source language models.
- Experience with LLM, RAG, or agent-based systems and their production challenges.
- Experience implementing authentication, rate limiting, quotas, token management, cost monitoring, or policy enforcement controls.
- Experience with cloud platforms, containerization, Kubernetes, and production observability.
- Experience with CI/CD, deployment automation, and reliable software release practices.
- Knowledge of relational databases and experience with vector search or vector databases.
- Strong written and spoken English.
- Preferred experience with LangChain, LangGraph, pgvector, FAISS, Pinecone, Weaviate, Databricks, Microsoft Foundry, Azure AI, AWS Bedrock, or Google Vertex AI.
- Preferred experience with LLM gateways, model routing, fallback strategies, multi-provider architectures, AI evaluation, prompt-injection testing, responsible AI, security governance, or FinOps controls.
- Strong problem-solving, communication, ownership, quality, security, and reliability skills, with the ability to work across technical and non-technical teams.
Benefits
- Permanent contract.
- Competitive compensation package based on experience, including private health insurance.
- 22 days of annual leave plus 3 additional company days.
- Flexible working hours and a hybrid work model in Porto.
- Continuous technical and behavioral learning opportunities.
- Modern office in central Porto with free parking.
- Access to ISS Tech Communities.
- Free company gym access, snacks, and drinks at the office.
Tech Stack
Categories
