Software Engineer - RAG

To get the best candidate experience, please consider applying for a maximum of 3 roles within 12 months to ensure you are not duplicating efforts.

Job Category

Job Details

About Salesforce

We're Salesforce, the Customer Company, inspiring the future of business with AI+ Data +CRM. Leading with our core values, we help companies across every industry blaze new trails and connect with customers in a whole new way. And, we empower you to be a Trailblazer, too - driving your performance and career growth, charting new paths, and improving the state of the world. If you believe in business as the greatest platform for change and in companies doing well and doing good - you've come to the right place.

Salesforce is leading the next wave of enterprise AI by building intelligent agents that deliver customer success 24/7. We're investing in cutting-edge Retrieval-Augmented Generation (RAG) systems that power generative AI platforms and applications used by millions of people globally. We're looking for a Software Engineer to join the Einstein Foundations team, focused on building scalable, reliable, and intelligent distributed systems that support RAG pipelines and services across Salesforce.

You'll be part of a diverse and high-impact team of software engineers, machine learning engineers, and data scientists. Our mission is to design and build next-generation AI infrastructure that powers everything from knowledge-grounded agents to large-scale enterprise search. We value collaboration, technical excellence, and a passion for solving hard systems problems.

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.

• 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.

• 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.

• 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.

Accommodations

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

Posting Statement

Salesforce is an equal opportunity employer and maintains a policy of non-discrimination with all employees and applicants for employment. What does that mean exactly? It means that at Salesforce, we believe in equality for all. And we believe we can lead the path to equality in part by creating a workplace that's inclusive, and free from discrimination. Know your rights: workplace discrimination is illegal. Any employee or potential employee will be assessed on the basis of merit, competence and qualifications - without regard to race, religion, color, national origin, sex, sexual orientation, gender expression or identity, transgender status, age, disability, veteran or marital status, political viewpoint, or other classifications protected by law. This policy applies to current and prospective employees, no matter where they are in their Salesforce employment journey. It also applies to recruiting, hiring, job assignment, compensation, promotion, benefits, training, assessment of job performance, discipline, termination, and everything in between. Recruiting, hiring, and promotion decisions at Salesforce are fair and based on merit. The same goes for compensation, benefits, promotions, transfers, reduction in workforce, recall, training, and education.