Publicis Sapient - Machine Learning Engineer - LLM Applications

Description :

Machine Learning Engineer LLM Applications

Overview :

We are looking for a Machine Learning Engineer with hands-on experience in productionizing Large Language Model (LLM) applications. The ideal candidate will be skilled at building scalable, reliable ML pipelines and deploying models to production environments.

Key Responsibilities :

- Design, develop and deploy LLM-based applications using scalable cloud infrastructure.

- Build and orchestrate data and model pipelines using Apache Airflow and GCP services (BigQuery, Vertex AI, Cloud Run, etc.).

- Implement retrieval-augmented generation (RAG) systems with vector databases (e.g., Pinecone, FAISS, Weaviate).

- Containerize, test and deploy ML workloads using Docker and Kubernetes.

- Maintain CI/CD workflows using Git, Jenkins, or similar tools.

- Monitor, optimize and troubleshoot production ML systems for reliability and performance.

Required Skills & Experience :

- Proven experience in LLM application development and MLOps.

- Strong proficiency in Python, TensorFlow/PyTorch and cloud-native ML pipelines.

- Hands-on expertise in GCP, Airflow, BigQuery, Docker and vector databases.

Good to Have :

- Familiarity with Kubernetes, Git, Jenkins and modern CI/CD practices.

- Understanding of embeddings, prompt engineering and model serving in production.

- Interest in RAG performance optimisation and benchmarking.