Salesforce Software Engineer - RAG 

United States, California, Palo Alto 

752647542

Job Category

Software Engineering

Job Details

The Role

As a Software Engineer on the Einstein RAG team, you'll play a key role in designing, implementing, and maintaining large-scale distributed systems that integrate deep learning models, retrieval pipelines, and enterprise data. You'll work across the AI stack—from building microservices and data pipelines to enabling real-time inference and document retrieval using modern ML techniques. You’ll partner with ML engineers, product managers, and researchers to operationalize LLMs and RAG services for production use at scale.

What You’ll Do:

• Design and build robust, scalable RAG systems that serve thousands of tenants and integrate with multiple Salesforce applications.
• Develop high-performance distributed systems for knowledge retrieval, document ranking, and grounding LLMs in structured and unstructured enterprise data.
• Build scalable APIs, microservices, and orchestration layers to support multi-stage RAG pipelines.
• Drive automation for deployment, monitoring, performance tuning, and root cause analysis.
• Collaborate with ML and AI platform teams to productionize retrieval services and integrate vector databases, embeddings, and search infrastructure.
• Ensure reliability, security, and performance of AI-backed systems in real-time, multi-tenant environments.
• Participate in on-call rotations and be a key player in debugging live issues and ensuring high availability.

Required Skills:

• 5+ years of experience building and maintaining large-scale distributed systems, data-intensive applications, or cloud-native services.
• Proficiency in system design, microservices architecture, and cloud-native tools (Docker, Kubernetes, etc.).
• Strong programming skills in Python and/or Java, with a deep understanding of system-level performance.
• Experience building scalable data pipelines using Kafka, Spark, Flink, or similar frameworks.
• Deep understanding of modern data storage, indexing, and retrieval frameworks (e.g., Elasticsearch, Redis, Hadoop, Cassandra).
• Familiarity with LLMs, embeddings, and retrieval-based architectures (e.g., RAG, vector search).
• Proven ability to take projects from ideation to production, with a strong bias for execution.
• Solid understanding of API design, versioning, and deployment in high-availability environments.

Preferred Skills:

• Experience integrating vector databases (e.g., FAISS, Weaviate, Pinecone) into production systems.
• Familiarity with prompt engineering, LLM fine-tuning, and hybrid retrieval architectures.
• Strong foundation in NLP, machine learning, or information retrieval.
• Experience working with unstructured data at scale, including document processing and semantic search.
• Background in observability, performance profiling, and scalable service infrastructure.
• Exposure to MLOps tools and CI/CD workflows for ML/AI systems.
• Prior work with generative AI or conversational AI systems in enterprise settings.
• Excellent communication and collaboration skills, with the ability to influence across engineering and product teams.

If you require assistance due to a disability applying for open positions please submit a request via this.

Posting Statement