Submit

AI Software Engineer (LLM / RAG applied to Telecom)

Lisboa

Job description

We are looking for an experienced AI Engineer for a hibrid position, in Lisbon, to integrate our proprietary SaaS. 

SimplAI, is an intelligent assistance layer integrated of Simplifyd, a platform focused on monitoring, optimization and operation of multi-technology mobile networks (2G/3G/4G/5G).
SimplAI uses LLM/RAG technologies to support engineering teams in technical information analysis, assisted troubleshooting, interpretation of optimization recommendations and operational contextualization.
The solution will be integrated with real telecommunications data, internal APIs and analytical modules already existing in the Simplifyd platform.

You will participate and develop in an AI product applied to telecommunications, having exposure to real problems and real data.
We want you to active participate in the product's technological evolution, and we provide the enviornment for technical growth within the organisation


Your Responsibilities will be:
  • Define and implement the LLM/RAG architecture: ingestion, chunking, embeddings, retrieval, reranking, metadata, versioning and source provenance
  • Create evaluation, tracing, regression testing and observability mechanisms
  • Ensure responses with identifiable sources, clear context and abstention when evidence is weak
  • Integrate SimplAI with existing Simplifyd APIs and components, designing the tool calling and function calling layer with traceability, clear authority boundaries and auditability of all invocations
  • Define technical and operational guardrails, including LLM authority boundaries
  • Work with internal telco specialists to transform RAN/SON knowledge into knowledge retrievable by the system
  • Prepare future integration with the SON Orchestrator, preserving the separation between cognitive assistance and operational decision-making
  • Technically lead the team and promote knowledge transfer


Requirements

  • 5–8+ years in software engineering, ML engineering, data engineering or related areas
  • Real experience with RAG systems in production — at least one system with real users, concrete decisions and real quality, latency or grounding issues
  • Practical LLMOps: golden datasets, tracing (Langfuse, Phoenix, LangSmith or equivalent), regression between versions, observability
  • Senior Python backend, APIs (FastAPI or equivalent) and integration in existing product
  • Ability to design robust systems and keep them operational, not just prototypes
  • Technical leadership of a small team with heterogeneous profiles
  • Clear understanding that LLMs do not replace deterministic engines in critical systems — and ability to defend that boundary
Valued requirements
  • Experience with LLM/RAG frameworks such as LangChain, LlamaIndex, Haystack or equivalents
  • Knowledge of vector databases such as FAISS, Qdrant, Milvus, Weaviate or similar
  • Familiarity with semantic search, hybrid search, reranking and retrieval/context strategies for LLMs
  • Observability, logging and troubleshooting applied to distributed systems
  • Knowledge of telecommunications, mobile networks or OSS/SON
  • Experience in data-driven and automation-oriented environments
  • Familiarity with tool calling in production and tool exposure protocols for LLMs (e.g. MCP), for controlled and auditable integration with external APIs and systems

What we are not looking for
  • Pure prompt engineer with no system experience
  • Researcher with no product or real users
  • Data scientist working exclusively in notebooks
  • Architect who does not implement
  • Candidates that views the LLM as an autonomous operational decision engine

Want to apply?
Position
Name*
Email*
Phone number*
Country*
City*
Linkedin
Faça upload do seu CV* (max. 4MB)
Upload your photo or video (max. 4MB)
Submit