Senior Generative AI Engineer

Job Description

We are seeking a Senior Generative AI Engineer to design, build, and take to production solutions based on large language models (LLMs). The ideal profile combines solid software engineering with hands-on experience in generative AI applications: RAG systems, agents, and business process automation. We are looking for someone capable of moving from proof of concept to a reliable, measurable, and secure product.

Main Responsibilities

• LLM Solutions: Design and develop applications based on language models (proprietary and open-source model APIs) integrated into real products.
• RAG & Semantic Search: Implement retrieval-augmented generation pipelines with vector databases, embeddings, and chunking and reranking strategies.
• Agents & Orchestration: Build agent-based workflows with tool use and multi-step orchestration to automate complex tasks.
• Evaluation & Quality: Define metrics and tests to measure accuracy, latency, cost, and hallucinations, and continuously improve results.
• Security & Best Practices: Apply guardrails, responsible handling of sensitive data, and AI governance criteria.
• Collaboration: Work with product, data, and engineering teams to identify use cases and take them to production.

Exclusionary Requirements

• Experience: 5+ years in software development and at least 1 to 2 years building LLM-based solutions in production.
• Programming: Advanced proficiency in Python and API design (FastAPI or similar).
• Generative AI: Experience with LLM APIs (OpenAI, Anthropic, Google, or open source), advanced prompting, and RAG techniques.
• Data: Knowledge of vector databases (pgvector, Pinecone, Weaviate, or similar) and SQL.
• Cloud: Experience with AWS, GCP, or Azure for deploying AI services.
• Engineering: Good practices in testing, CI/CD, and version control with Git.

Desirable (Plus)

• Frameworks: Experience with LangChain, LlamaIndex, or agent frameworks.
• Fine-tuning & Custom Models: Fine-tuning, open-source models, or local LLM deployment.
• MLOps / LLMOps: Monitoring, tracing, and versioning of prompts and models.
• Containerization: Docker and Kubernetes.
• Soft Skills: Ability to translate business needs into clear, measurable AI solutions.