Agentic AI Software Engineer

Community Of
Municipality of Madrid, Spain
yesterday

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English
Experience level
Senior

Job location

Remote
Municipality of Madrid, Spain

Tech stack

API
Artificial Intelligence
Amazon Web Services (AWS)
Amazon Web Services (AWS)
Bioinformatics
C++
Cloud Computing
Code Review
Encodings
Computer Programming
Databases
Continuous Integration
Information Engineering
Relational Databases
Database Queries
Python
Machine Learning
OAuth
Query Optimization
Software Construction
Software Engineering
Data Processing
Retrieval-Augmented Generation
Large Language Models
Multi-Agent Systems
Database Optimization
Prompt Engineering
Backend
FastAPI
Build Management
Pytest
Git Flow
Integration Tests
Information Technology
Production Code
Virtual Agents
REST
GPT

Requirements

Location: Remote from EUROPE About the Company Our client is a global, science-driven biopharmaceutical company (top 10 worldwide) focused on discovering, developing, and delivering innovative medicines and healthcare solutions that improve patients' lives. They are heavily investing in AI and are building advanced Agentic AI solutions to accelerate scientific research and decision-making across the organization. Role Overview We are looking for a highly skilled Senior Agentic AI Software Engineer with strong software engineering fundamentals and deep Python expertise. In this role, you will design and build Agentic AI systems that automate complex data and analysis workflows across multiple scientific domains. You will work closely with other engineers, data scientists, and domain experts to turn high-level research and business needs into robust, scalable, and production-grade AI solutions. Key Responsibilities * Design, implement, and maintain Agentic AI solutions (LLM-powered agents, tools, and workflows) for scientific and data-intensive use cases. * Build and support tools to orchestrate data processing, analysis, and decision-making pipelines. * Automate complex, multi-step workflows using Python and modern AI/LLM frameworks. * Integrate AI agents with internal systems and data sources via APIs, databases, and services. * Ensure robustness, observability, and performance of Agentic AI systems in production. * Apply software engineering best practices (testing, code review, CI/CD, documentation, monitoring). * Design and develop MCP servers to connect and access internal data sources. Essential Qualifications * University degree in Computer Science, Engineering, Bioinformatics, or related field (M.Sc. or PhD is a plus). * 5+ years of professional experience in software engineering, data engineering, data science, machine learning, or related areas. * Strong, hands-on Python programming skills (writing production-grade code, libraries, and services). Experience working with: * Advanced RDBMS & Data Modeling: Expert-level SQL proficiency, including query optimization, indexing strategies, and handling complex relational schemas. * Production-Grade APIs: Extensive experience designing and consuming robust RESTful services, focusing on scalability, security (OAuth/JWT), and high-concurrency integration. * Cloud Infrastructure (AWS Priority): Hands-on experience architecting and deploying Python applications in AWS (ECS, Lambda, S3, RDS) using Infrastructure as Code (IaC) principles. * Software Engineering Excellence: A rigorous track record of applying best practices: Gitflow, unit/integration testing (PyTest), automated CI/CD pipelines, and conducting high-standard code reviews. Highly Valued (Nice to Have): * Agentic AI Systems in Production: Proven experience building or orchestrating multi-agent systems (LLM-based) with complex tool-calling capabilities and autonomous decision-making loops. * Enterprise AI Frameworks: Deep familiarity with modern orchestration layers such as Pydantic-AI, LangGraph, or Semantic Kernel, moving beyond basic linear chains. * Advanced RAG Architectures: Practical experience with Retrieval-Augmented Generation, including vector database tuning (e.g.,Pinecone, Weaviate, Milvus), embedding optimization, and metadata filtering. * LLM Lifecycle & Evaluation: Strong understanding of foundation model constraints, prompt engineering for production (DSPy/evaluation frameworks), and managing token latency/cost. * Polyglot Programming: Experience in at least one compiled language (e.g., Go, C++, or Rust) to handle performance-critical backend components or low-level optimizations. * Data domain knowledge: Experience working with scientific data (Omics, Imaging, Clinical, Preclinical, etc..).

Apply for this position