Salesforce, Inc..
Sr. Software Engineer - AI Agents
Salesforce, Inc.., San Francisco, California, United States, 94199
*IN SCHOOL OR GRADUATED WITHIN THE LAST 12 MONTHS? PLEASE VISIT FUTURE FORCE FOR OPPORTUNITIES *
About Salesforce:
Salesforce is the #1 AI CRM, empowering companies to connect with their customers in a whole new way. We are a fast-paced, innovative company that values collaboration, customer success, and continuous learning. Our team is at the forefront of leveraging cutting-edge AI technologies to build intelligent systems that transform how businesses operate.
About the Team:
The Digital Marketing Technology Agent Engineering team at Salesforce is dedicated to building the next generation of intelligent agents that enhance productivity, automate tasks, and provide personalized experiences for our customers. We specifically focus on Agentforce, leveraging advanced generative AI services, pipelines, and components to deliver robust agent solutions. We work with state-of-the-art AI models, including Large Language Models (LLMs), and develop sophisticated agentic systems to solve complex business problems. As a lead member, you will play a pivotal role in shaping our technical vision, driving innovation, and mentoring junior engineers with a significant focus on architectural design and implementation of highly scalable and reliable distributed systems that power our AI capabilities.
Role Overview:
We are looking for a highly skilled and experienced Lead Member of Technical Staff (LMTS) to join our Agent Engineering team. In this role, you'll be responsible for leading the design, development, and deployment of advanced AI agents and the underlying distributed systems that support them for Agentforce. This role requires a strong focus on distributed systems architecture, scalability, reliability, and performance, applied to building cutting-edge intelligent agent platforms that leverage AI, RAG (Retrieval-Augmented Generation), and LLMs.
Responsibilities:
Lead the end-to-end design, development, and deployment of intelligent agents and agentic systems for Agentforce. This involves applying AI, LLMs, and RAG techniques while building highly scalable, resilient, and performant distributed architectures.
Ensure solutions are designed for distributed deployment, operational excellence, and long-term maintainability.
Architect and implement robust and efficient data pipelines and service integrations that support complex AI functionalities, including mechanisms for contextual retrieval, citations, and responsible AI behaviors within a distributed environment.
Research, evaluate, and integrate the latest LLM algorithms and AI technologies into our agent solutions, considering their implications and performance in a distributed setting.
Design and build frameworks for distributed orchestration, inter-service communication, and collaboration within a multi-agent environment, specifically focusing on reliable messaging, distributed state management, and fault tolerance strategies.
Champion software engineering best practices, including code quality, test automation, and robust monitoring for distributed systems that host AI models.
Foster a culture of technical excellence and continuous learning, including principles of distributed systems design and operation.
Actively participate in the full software development lifecycle, from architectural ideation to deployment, monitoring, and post-launch optimization of distributed services that power our AI agents.
Collaborate closely with product managers, AI researchers, and other engineering teams to define requirements and design scalable AI-driven solutions and develop reusable components and workflows for Agentforce.
Troubleshoot and resolve complex technical issues related to system performance, scalability, reliability, and data consistency in large-scale distributed environments supporting AI applications.
Stay up-to-date with industry trends and emerging technologies in AI, agent systems, distributed computing, and cloud-native architectures.
Required Skills and Experience: 8+ years of professional software development experience, with a strong focus on backend systems and distributed applications.
Bachelor's or Master's degree in Computer Science, Software Engineering, or a related STEM field.
Extensive experience in designing, building, and operating highly available, scalable, and fault-tolerant distributed systems.
Proven experience with Large Language Models (LLMs), including fine-tuning, prompt engineering, and deployment strategies.
Strong practical experience with Retrieval-Augmented Generation (RAG) systems, including vector databases, indexing, retrieval algorithms, and knowledge graph integration.
Proficiency in at least one modern programming language (e.g., Python, Java, Go), with a firm grasp of data structures, algorithms, and object-oriented design.
Practical experience with cloud platforms (AWS, Azure, GCP) and deploying large-scale applications within cloud-native architectures.
Demonstrated experience with distributed data storage solutions (e.g., NoSQL databases, distributed caches, distributed file systems) and stream processing frameworks (e.g., Apache Flink, Spark Streaming).
Strong understanding of software architecture patterns (e.g., microservices, event-driven architectures) and their application in distributed environments.
Demonstrated ability to lead technical initiatives, drive innovation, and mentor other engineers on complex software engineering and AI-related challenges.
Excellent problem-solving, analytical, and communication skills, particularly in explaining complex technical concepts.
Desired Skills and Experience: Experience with containerization technologies (e.g., Docker, Kubernetes) and orchestration in production.
Familiarity with CI/CD pipelines and DevOps practices for distributed AI systems.
Experience with monitoring, logging, and tracing tools for distributed applications.
Experience with MLOps practices for deploying and managing AI models in production.
Experience in natural language understanding (NLU) and natural language generation (NLG).
Experience with the implementation of citations and guardrails for LLMs.
Why Salesforce? Work on cutting-edge AI technologies that are transforming industries, specifically for our Agentforce initiative.
Collaborate with a world-class team of engineers and researchers.
Opportunity to make a significant impact on our products and customers.
Continuous learning and development opportunities.
Competitive compensation and benefits package.
#LI-Y #J-18808-Ljbffr
Ensure solutions are designed for distributed deployment, operational excellence, and long-term maintainability.
Architect and implement robust and efficient data pipelines and service integrations that support complex AI functionalities, including mechanisms for contextual retrieval, citations, and responsible AI behaviors within a distributed environment.
Research, evaluate, and integrate the latest LLM algorithms and AI technologies into our agent solutions, considering their implications and performance in a distributed setting.
Design and build frameworks for distributed orchestration, inter-service communication, and collaboration within a multi-agent environment, specifically focusing on reliable messaging, distributed state management, and fault tolerance strategies.
Champion software engineering best practices, including code quality, test automation, and robust monitoring for distributed systems that host AI models.
Foster a culture of technical excellence and continuous learning, including principles of distributed systems design and operation.
Actively participate in the full software development lifecycle, from architectural ideation to deployment, monitoring, and post-launch optimization of distributed services that power our AI agents.
Collaborate closely with product managers, AI researchers, and other engineering teams to define requirements and design scalable AI-driven solutions and develop reusable components and workflows for Agentforce.
Troubleshoot and resolve complex technical issues related to system performance, scalability, reliability, and data consistency in large-scale distributed environments supporting AI applications.
Stay up-to-date with industry trends and emerging technologies in AI, agent systems, distributed computing, and cloud-native architectures.
Required Skills and Experience: 8+ years of professional software development experience, with a strong focus on backend systems and distributed applications.
Bachelor's or Master's degree in Computer Science, Software Engineering, or a related STEM field.
Extensive experience in designing, building, and operating highly available, scalable, and fault-tolerant distributed systems.
Proven experience with Large Language Models (LLMs), including fine-tuning, prompt engineering, and deployment strategies.
Strong practical experience with Retrieval-Augmented Generation (RAG) systems, including vector databases, indexing, retrieval algorithms, and knowledge graph integration.
Proficiency in at least one modern programming language (e.g., Python, Java, Go), with a firm grasp of data structures, algorithms, and object-oriented design.
Practical experience with cloud platforms (AWS, Azure, GCP) and deploying large-scale applications within cloud-native architectures.
Demonstrated experience with distributed data storage solutions (e.g., NoSQL databases, distributed caches, distributed file systems) and stream processing frameworks (e.g., Apache Flink, Spark Streaming).
Strong understanding of software architecture patterns (e.g., microservices, event-driven architectures) and their application in distributed environments.
Demonstrated ability to lead technical initiatives, drive innovation, and mentor other engineers on complex software engineering and AI-related challenges.
Excellent problem-solving, analytical, and communication skills, particularly in explaining complex technical concepts.
Desired Skills and Experience: Experience with containerization technologies (e.g., Docker, Kubernetes) and orchestration in production.
Familiarity with CI/CD pipelines and DevOps practices for distributed AI systems.
Experience with monitoring, logging, and tracing tools for distributed applications.
Experience with MLOps practices for deploying and managing AI models in production.
Experience in natural language understanding (NLU) and natural language generation (NLG).
Experience with the implementation of citations and guardrails for LLMs.
Why Salesforce? Work on cutting-edge AI technologies that are transforming industries, specifically for our Agentforce initiative.
Collaborate with a world-class team of engineers and researchers.
Opportunity to make a significant impact on our products and customers.
Continuous learning and development opportunities.
Competitive compensation and benefits package.
#LI-Y #J-18808-Ljbffr