Senior Software Engineer

Incorta is an enterprise data and analytics platform. The Incorta AI Gateway is the single, governed path that every AI call in Incorta takes, from Incorta's products and services to models such as Claude. It decides who can call which model, enforces budgets and safety rules, and records what every call cost.

As a Senior Engineer, you'll design, build, and run major parts of the gateway, from the request path to the admin consoles. You'll own features from design to production, and you'll write a lot of the code yourself.

YOU WILL

• Build core backend services in Go, including authorization, budgets, credit accounting, model routing, fallback, guardrails, and usage reporting.

• Develop and optimize the data plane to ensure streaming, tool calls, and LLM APIs (such as Anthropic and OpenAI) remain fast, robust, and accurate.

• Own end-to-end features in production on Kubernetes and AWS, writing design docs, migrations, and comprehensive tests.

• Partner with product, design, and security teams to shape gateway APIs, Terraform providers, and admin consoles.

• Participate in code reviews, mentor teammates, and maintain high engineering standards across services.

YOU HAVE

• Typically 6+ years building and shipping backend software, including production services that other teams or customers depend on.
• Strong hands-on Go, or strong experience in another backend language (Java, Rust, C++ or TypeScript) and a willingness to work in Go every day.
• Experience building or running high-traffic APIs: HTTP, streaming (server-sent events), retries, timeouts and rate limits.
• Working knowledge of authentication and authorization: OAuth 2.0, OIDC and JWT, and how to keep secrets out of code and databases.
• Hands-on experience with containers and Kubernetes on a major public cloud (AWS preferred): Helm, deployments, logs, metrics and on-call.
• Solid SQL and database design: PostgreSQL or SQLite, schema migrations, transactions and correctness when many requests run at once.
• Experience integrating large language model (LLM) APIs into a product: streaming responses, tool calling, and the trade-offs between quality, speed and cost.
• A habit of testing: unit, integration and end-to-end tests that catch real bugs, and code reviews that make the code better.
• Clear writing: design documents and pull requests your teammates can follow.
• Excellent written and spoken English, for working with teams across time zones.
• A bachelor's degree in Computer Science or Engineering, or equivalent practical experience.

NICE TO HAVE

• Experience with API gateways, proxies, or service meshes (Envoy, agentgateway, Kong, LiteLLM, xDS) or open-source networking projects.

• Work on AI safety, guardrails (prompt injection defense, PII masking), and LLM evaluation frameworks.

• Experience with usage metering/billing systems, multi-tenant SaaS, Terraform provider development, or full-stack React/TypeScript development.

• Familiarity with AI coding agents and protocols (Claude Code, MCP).