SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 177,000 - 216,000 / annual
Metropolis is pioneering the Recognition Economy, using AI to transform real-world experiences like parking, retail, and hospitality into seamless, intelligent interactions. The company is seeking a Senior Software Engineer to architect and build the AI agent swarm, orchestration pipelines, and developer tooling that power this platform.
In this role, you will design and build production-grade agentic platform infrastructure, including agent harnesses, orchestration pipelines, tool-use abstractions, MCP integrations, and context/memory management systems. You'll architect high-throughput, low-latency LLM inference routing with caching strategies and semantic search interfaces to optimize cost, performance, and token usage. You will establish robust evaluation, tracing, and observability frameworks (LLMOps/AIOps) to measure agent accuracy, monitor execution paths, and debug non-deterministic workflows.
You'll build developer tooling, agent SDKs, and CI/CD automation that empower product engineering teams to deploy autonomous AI agents safely and efficiently. You'll implement enterprise-grade guardrails, rate-limiting, sandboxing, and security policies for model execution and tool access. You'll make critical architectural choices regarding service boundaries, data consistency, multi-agent communication protocols, and overall system reliability. You'll also drive technical standards, evaluate emerging AI tooling, and mentor engineering peers on agentic architectural patterns.
The role requires collaboration across Application Engineering, Infrastructure, and Advanced Technologies teams. You'll work alongside highly technical engineers focused on performance optimization, model routing, reliability engineering, and agent protocols. Metropolis operates on an office-first model requiring at least four days per week on-site in Seattle to foster innovation and culture.
Tech stack includes TypeScript, React, Scala, Java, MySQL, PostgreSQL, Snowflake, AWS, Git/GitHub, Claude Code, GitHub Copilot, and Datadog.
REQUIREMENTS:
- 6+ years of backend software engineering experience with deep focus on distributed systems, platform infrastructure, and high-load production environments
- 2+ years of hands-on experience architecting and deploying agentic AI systems, LLM orchestration frameworks, or AI platform tooling
- Strong proficiency in Python or Java/TypeScript with production expertise in async concurrency, API design, and system performance tuning
- Production experience with modern agentic orchestration frameworks and protocols such as LangGraph, Anthropic MCP, Google ADK, AutoGen, A2A, or LlamaIndex
- Expertise in microservices architecture, container orchestration (Kubernetes), and cloud platforms (AWS)
- Observability and LLMOps expertise, including metrics, distributed tracing, structured logging, and debugging agent execution runs
- Database and data systems knowledge including relational databases, vector databases, event streaming (Kafka, SQS), and caching patterns
- Demonstrated experience leveraging AI-powered development tools such as Claude Code, GitHub Copilot, or similar agentic coding tools
- Excellent technical communication with ability to design and document complex AI architectures
PLUS (not required):
- Advanced degree in Computer Science, Machine Learning, or related technical field
- Experience building customized agent harnesses, fine-tuning models, or implementing RLHF/RLAIF optimization loops
- Security compliance expertise regarding data privacy, prompt injection defenses, secrets management, and access controls for financial or mobility data
- Contributions to open-source agent frameworks, MCP servers, or technical writing on agentic system architectures
