Senior Backend Engineer (GenAI)

We are looking for a Senior Backend Engineer with a strong GenAI background to join our team and work 100% dedicated on a strategic project for one of our top clients in the pharmaceutical sector. In this role, you will design and build advanced backend and AI-driven systems, contributing to the evolution of an enterprise knowledge platform powered by Retrieval-Augmented Generation (RAG) and agentic architectures.

Main Responsibilities

• Design and implement RAG architectures and agentic workflows to improve accuracy, relevance, and performance of AI-powered search and knowledge systems.
• Develop high-quality, modular, and maintainable Python backend services, with a strong focus on testing, type hinting, and clean architecture.
• Build and operate document processing and data pipelines to transform unstructured data into AI-ready formats (e.g. using Airflow, AWS Glue, OCR tools).
• Integrate backend services across complex enterprise systems, including integrations via platforms such as Snaplogic.
• Manage and optimize AWS cloud infrastructure (ECS, EC2, VPC, Lambda) ensuring scalability, security, and cost efficiency.
• Own CI/CD pipelines and containerized workloads using Docker.
• Provide technical leadership to external vendor teams, validating deliverables, guiding architecture decisions, and internalizing platform knowledge.

• Bachelor's or Master's degree in Computer Science, Engineering, or a related field.
• 5+ years of experience in backend engineering with ownership of complex systems.
• Advanced software engineering expertise, with a strong focus on modularity, testability, and clean architecture.
• Strong professional experience in Python (code quality, testing, type hinting).
• Proven experience designing RAG architectures and agentic workflows.
• Hands-on experience with LLM frameworks (e.g. LangChain, LlamaIndex) and vector databases (Pinecone, Milvus, Chroma or similar).
• Solid experience with AWS cloud infrastructure (ECS, EC2, VPC, Lambda).
• Experience implementing Infrastructure as Code (Terraform, CloudFormation, or AWS CDK).
• High level of autonomy, strong communication skills, and ability to document and explain architectural decisions.
• Fluent English (written and spoken).

Desirable / Nice to Have

• Experience building data engineering pipelines (Apache Airflow, AWS Glue, OCR solutions).
• Familiarity with Snaplogic or similar enterprise integration platforms.
• Exposure to semantic technologies or knowledge graphs (Neo4j, RDF/SPARQL).
• Experience with LLM evaluation and observability tools (Langfuse, Arize, MLflow).
• Experience working in regulated or enterprise environments, ideally within pharma or similar industries.