Software Engineering Architect

Salesforce•San Francisco, CA

About The Position

Salesforce is seeking an Architect to set strategy and technical direction for its internal agentic platform, Model Context Protocol (MCP), LLM Model Gateway, and context engineering capabilities. This hands-on architecture role will shape how agents are built, connected to tools and models, grounded in enterprise knowledge, and used across the software development lifecycle (SDLC). The architect will help teams adopt AI safely, improve developer productivity, and use shared platform capabilities rather than duplicating solutions. The role guides platform architecture and adoption, including agent orchestration and runtimes, MCP patterns, model access and governance, enterprise retrieval and knowledge systems, and AI-enabled developer experiences. It also sets shared standards for security, privacy, reliability, observability, evaluation, and human oversight. The architect stays involved in implementation by prototyping, validating designs through working systems, reviewing critical work, resolving technical tradeoffs, aligning partners across functions, and mentoring engineers and technical leaders. The successful candidate has 15+ years of experience designing and delivering large-scale distributed systems, developer platforms, AI platforms, or infrastructure services, and a related technical degree. Salesforce also offers benefits including time off programs, medical, dental, vision, mental health support, paid parental leave, life and disability insurance, 401(k), and an employee stock purchasing program. The typical annual base salary range is $218,400–$365,200, or $263,200–$401,400 in select San Francisco and New York City metropolitan locations; ranges are base salary only.

Requirements

15+ years of experience designing and delivering large-scale distributed systems, developer platforms, AI platforms, or infrastructure services.
Track record of setting strategy and technical direction across teams and carrying it through implementation and production operation.
Strong expertise in agentic platform architecture and experience creating capabilities that make agent development and operation effective for application teams.
Hands-on experience with agentic frameworks such as Mastra AI and LangChain/LangGraph, including evaluating tradeoffs and establishing scalable platform patterns.
Experience designing model gateways, inference platforms, model-serving systems, model orchestration layers, or equivalent shared services.
Experience evaluating models against real workloads and understanding quality, latency, throughput, reliability, and cost tradeoffs.
Familiarity with SLMs, LLMs, model routing, fine-tuning, quantization, inference optimization, or other methods to improve cost and performance.
Experience building enterprise knowledge or retrieval systems using RAG, Graph RAG, search, or related approaches.
Experience designing APIs and extensible integration patterns.
Expertise in one or more relevant areas such as identity and authorization, data platforms, retrieval and search, context management, workflow orchestration, platform security, or developer experience.
Understanding of software development workflows and how to assess whether AI improves developer experience, productivity, and engineering outcomes.
Sound judgment around security, privacy, reliability, performance, and operational cost in fast-changing technical environments.
Strong communication skills and ability to build alignment across engineering, product, security, and business teams.
Genuine AI-first approach to engineering; use of AI tools such as Claude Code, GitHub Copilot, Codex, or Cursor and ability to write precise, structured prompts for reliable, secure, production-ready output.
A related technical degree is required.

Nice To Haves

Familiarity with MCP or comparable tool and protocol ecosystems.
Experience delivering production LLM or agent systems, including evaluation, telemetry, safety, and operational feedback loops.
Experience with coding assistants, AI-enabled developer tools, CI/CD workflows, automated testing, code review, or software engineering productivity initiatives.
Experience building internal platforms, paved paths, or developer tools adopted by multiple teams.
Experience with multi-model architectures spanning commercial APIs, open-weight models, and self-hosted or specialized models.
Contributions to technical standards, open-source projects, or cross-organization architecture initiatives.

Responsibilities

Own strategy and architecture for a shared agentic platform that enables teams to build, compose, deploy, and operate agents across Salesforce.
Set architecture and adoption direction for MCP, including server and client patterns, tool discovery, interoperability, identity, authorization, and lifecycle management.
Define reusable platform capabilities for agent orchestration, tool and skill integration, agent runtimes, state and memory, human oversight, evaluation, and production operations.
Guide agentic framework adoption and integration, including Mastra AI and LangChain/LangGraph, while keeping the platform coherent and extensible.
Establish paths and patterns for moving agents from prototypes to dependable production systems, including customization, evaluation, observability, and continuous improvement.
Drive AI-enabled developer experiences across the SDLC, including code understanding and generation, testing, code review, debugging, modernization, documentation, release, and operational workflows.
Define how MCP integrates with agent runtimes and the broader platform to support secure, governed, reusable connections to enterprise tools and systems.
Define the architecture and evolution of a secure, extensible LLM Model Gateway with consistent model access, policy enforcement, observability, resilience, and governance.
Drive a cost-effective portfolio of SLMs and LLMs and evaluate hosted, open-weight, fine-tuned, and specialized models for different workloads.
Develop methods to measure and improve model economics, including cost per successful task, token and context efficiency, retry rates, inference utilization, and the impact of model or routing changes.
Own strategy for context engineering and enterprise knowledge management so agents access relevant, grounded, permission-aware information.
Guide enterprise retrieval architecture, including RAG and Graph RAG, and how it works with enterprise data, knowledge sources, and agent workflows.
Set shared standards for security, privacy, governance, reliability, observability, evaluation, and human oversight across agents, models, tools, and data.
Prototype ideas, validate architecture through working systems, review critical designs, and help teams resolve technical tradeoffs.
Align engineering, product, security, data, and infrastructure partners around platform strategy, adoption, and delivery.
Communicate architectural decisions, influence across teams, and mentor engineers and technical leaders.
Design complex systems that integrate AI agents into human workflows and ship secure, high-quality software using AI in the development workflow.
Build and maintain shared system context for accurate AI work, and review human- or AI-written code for correctness, quality, security, and performance.