Desarrollador/a Fullstack

Tendios

. Design AI systems for extraction, classification, matching, summarisation, drafting and agentic workflows over tender documentation .

Posted 10/9/2026full-timeBarcelona • SpainMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in designing and deploying AI systems, particularly in extraction and classification workflows, while effectively managing commercial LLM providers and optimizing cost and performance metrics. Proficient in building and fine-tuning machine learning models, with a strong focus on production-ready solutions using Python, TypeScript, and Node.js.

Highest-signal resume keywords

5+ Years Software Engineering ExperienceStrong Python for ML WorkSolid TypeScript and Node.js ExperienceDeep Knowledge of Commercial LLM APIsProduction RAG Experience

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Machine LearningFine-Tuning ModelsQuantisationEmbeddingsHybrid RetrievalRerankingData Pipeline DevelopmentAPI DevelopmentRegression TestingCost Management

Soft Skills

CollaborationProblem-SolvingCommunication

Tools & Technologies

PyTorchHugging Face TransformersNode.jsNestJSDockerCI/CDCloud InfrastructureVLLMTGILlama.cpp

Industry Keywords

AI SystemsLLM EngineeringDocument AIGDPR AwarenessEU AI Act Awareness

Tech Stack

Tools & technologies

CloudDockerJavaScriptNode.jsPythonPyTorchTypeScript

About the role

Key responsibilities & impact

Design AI systems for extraction, classification, matching, summarisation, drafting and agentic workflows over tender documentation
Select and justify prompting, RAG, fine-tuning, distillation or classic ML approaches based on quality, latency and cost
Build retrieval pipelines with chunking, embeddings, hybrid search and reranking
Manage commercial LLM providers and control cost per feature
Apply prompt caching, batch APIs, model routing, cascading, semantic caching, context compression and token budgets
Track cost, latency and quality per feature and customer, and set alerts
Evaluate, fine-tune and deploy open-weight models such as Llama, Mistral, Qwen and Gemma
Serve models efficiently using vLLM, TGI or llama.cpp with quantisation and batching
Build data pipelines and labelled datasets for training and evaluation
Ship end-to-end AI features in Node.js/NestJS/TypeScript, including APIs, background jobs, streaming responses and integrations
Build evaluation suites and regression tests
Propose AI-driven features with product and promote LLM engineering practices
Work in the AI & Data squad alongside product squads

Requirements

What you’ll need

5+ years of software engineering, including 2+ years building LLM or ML features that run in production
Strong Python for ML work: PyTorch, Hugging Face Transformers and surrounding data tooling
Solid TypeScript and Node.js in production; NestJS experience or ability to become productive quickly
Deep hands-on knowledge of commercial LLM APIs and concrete cost-reduction experience
Practical experience fine-tuning, quantising and serving open-source models
Production RAG experience: embeddings, vector search, hybrid retrieval and reranking
Experience building test sets, using LLM-as-judge carefully and measuring improvements
Comfort with Docker, CI/CD, cloud infrastructure, observability and on-call ownership
Fluent English for technical work
Nice to have: Spanish; agents and tool use; document AI; LLM observability and gateway tools; GPU infrastructure and cost management; public procurement or document-heavy domain knowledge; GDPR and EU AI Act awareness