Staff Software Engineer – Core AI Platform

Описание вакансии

Staff Software Engineer – Core AI Platform (MCP & Agent Infrastructure)

As a Staff Software Engineer on the Core AI Platform team, you will lead the design and development of the foundational platform that powers Dojo AI agents at Sumo Logic. You will own the architecture and implementation of a robust, scalable MCP (Model Context Protocol)–based platform that enables AI agents to securely access context, invoke tools securely, and interact with enterprise systems in real time.

In this role, you will build and operate the core MCP server infrastructure, including frameworks for hosting first‑party MCP servers, federating with external and third‑party MCP servers, and orchestrating agent interactions across distributed environments. You will design systems that allow agents to reason over real‑time and historical context, manage conversation state and memory, and reliably execute tool calls with strong guarantees around fault tolerance, retries, idempotency, and isolation.

You will also architect the agent communication layer, enabling seamless integrations with systems such as Slack, Microsoft Teams, and other event‑driven communication platforms, allowing agents to be invoked from messages, threads, and workflows. Your work will ensure secure handling of credentials, webhooks, and streaming events while supporting multi‑tenant execution at enterprise scale.

A key part of your responsibility will be building deep observability and reliability into the platform—providing visibility into MCP interactions, agent decision paths, and tool executions; enabling monitoring, alerting, and debugging of non‑deterministic agent behavior; and enforcing rate limits, quotas, and backpressure to ensure platform stability.

Responsibilities

• Architect MCP-first platforms

• Design scalable, fault-tolerant infrastructure for hosting and operating MCP servers
• Define standards for MCP server onboarding, versioning, and interoperability

• Build federated context systems

• Enable agents to retrieve and reason over context from multiple internal and external MCP servers
• Design secure, low-latency context propagation and caching strategies

• Lead agent-to-tool communication design

• Build resilient tool invocation frameworks that handle partial failures gracefully
• Ensure deterministic execution paths where possible in probabilistic AI systems

• Enable conversational agent ecosystems

• Architect integrations with Slack, Teams, and similar platforms for real-time agent interactions
• Design event-driven systems for message ingestion, agent response, and feedback loops

• Drive technical leadership

• Lead architecture and design reviews across AI, platform, and product teams
• Mentor engineers and establish best practices for building AI infrastructure

• Operate at scale

• Continuously improve platform scalability, reliability, latency, and cost efficiency
• Own production readiness, incident response patterns, and operational excellence

Required Qualifications and Skills

• B.S. in Computer Science or related discipline (M.S. preferred)
• 8+ years of experience building large-scale, distributed backend systems
• Deep distributed systems expertise

• Microservices, async/event-driven systems, and fault-tolerant architectures

• Strong backend programming skills

• Java, Scala, Go, or Python with solid object-oriented design principles

• Concurrency & async programming

• Multi-threading, non-blocking I/O, and message-driven architectures

• API & protocol design

• Experience designing extensible APIs and protocol-based integrations

• Production systems experience

• Operating 24x7 multi-tenant services with SLAs and on-call ownership

• MCP (Model Context Protocol) expertise

• Hands-on experience building or operating MCP servers or similar agent protocols

• Federated systems

• Experience integrating with external services across trust boundaries

• Agent & LLM platforms

• Experience building AI agent infrastructure (LangChain, LangGraph, CrewAI, AutoGen, etc.)

• AWS cloud-native

• EC2, ECS/EKS, Lambda, SQS, DynamoDB, CloudWatch

• Infrastructure as Code

• Terraform, OpenAPI, CI/CD pipelines

• Security

• OAuth, token exchange, secrets management, and multi-tenant isolation

Desired Qualifications and Skills

• Tool calling / plugin systems

• Designed extensible tool registries or function-calling frameworks

• Communication platforms

• Slack, Microsoft Teams, or webhook-based event systems

• Observability

• Distributed tracing, metrics, structured logging (OpenTelemetry a plus)

About Us

Sumo Logic, Inc. helps make the digital world secure, fast, and reliable by unifying critical security and operational data through its Intelligent Operations Platform. Built to address the increasing complexity of modern cybersecurity and cloud operations challenges, we empower digital teams to move from reaction to readiness—combining agentic AI-powered SIEM and log analytics into a single platform to detect, investigate, and resolve modern challenges. Customers around the world rely on Sumo Logic for trusted insights to protect against security threats, ensure reliability, and gain powerful insights into their digital environments. For more information, visitwww.sumologic.com.

Sumo Logic Privacy Policy. Employees will be responsible for complying with applicable federal privacy laws and regulations, as well as organizational policies related to data protection.

The expected annual base salary range for this position is $207,000 - $243,000. Compensation varies based on a variety of factors, which include (but aren’t limited to) role level, skills and competencies, qualifications, knowledge, location, and experience. In addition to base pay, certain roles are eligible to participate in our bonus or commission plans, as well as our benefits offerings and equity awards.

Must be authorized to work in the United States at the time of hire and for the duration of employment. At this time, we are not able to offer non-immigrant visa sponsorship for this position.