KEY RESPONSABILITIES
- Design and implement GenAI applications using LLMs, embeddings, and prompt orchestration patterns.
- Build and optimize retrieval-augmented generation (RAG) pipelines and supporting components.
- Develop and maintain integrations with vector databases, APIs, and enterprise data sources.
- Engineer prompts, evaluation strategies, and guardrails for quality, relevance, and safety.
- Collaborate with product, architecture, and security teams to design scalable GenAI solutions.
- Monitor GenAI application performance, cost, latency, and output quality.
- Implement version control, testing, and deployment workflows for GenAI assets.
- Support troubleshooting, iterative tuning, and operational improvement of GenAI applications.
- Document solution design, limitations, risks, and technical decisions.

REQUIREMENTS
- Strong Python skills and hands-on experience building AI applications.
- Practical experience with LLM ecosystems and orchestration frameworks.




- Solid understanding of prompt engineering, RAG, embeddings, and vector search concepts.
- Experience integrating AI services through APIs and enterprise systems.
- Familiarity with cloud environments and containerization basics.
- Hands-on with Git and basic CI/CD practices.
- Awareness of AI risks such as hallucinations, privacy, prompt injection, and governance needs.
- Solid communication, experimentation mindset, and pragmatic problem-solving.

NICE-TO-HAVE
- Familiarity with vector databases and semantic search solutions.
- Exposure to fine-tuning, evaluation frameworks, or agentic workflows.
- Knowledge of responsible AI, security controls, and enterprise AI governance.
- Experience balancing model quality, latency, and cost in production use cases.

📌 Generative AI Engineer (Mumbai)
🏢 Saint-Gobain
📍 Mumbai