Developer Experience Engineer - Tulip Interfaces

OpenTalent; Somerville (MA); On-site; USD 140,000 - 190,000; Full time

Job summary

OpenTalent in Somerville, MA is seeking a Senior Software Engineer focused on developer tooling and agentic AI to build the internal platform that engineers rely on daily. You will design and ship components across code generation, tooling, MCP servers, and integrations with source control and CI/CD, shaping the standards for agent evaluation, deployment, and secure tool access.

The ideal candidate has 5+ years of software engineering, strong TS, API design, hands-on AI/LLMs, and collaboration

Qualifications

• 5+ years of software engineering experience with developer tooling or internal platforms.
• A proven ability to ship AI-enabled tooling for engineers and scale adoption.
• Strong fundamentals in TS, API design, and modern web tech.
• Experience with AWS, CI/CD, and security in code execution.

Responsibilities

• Partner with engineering teams to identify high-impact AI opportunities in the developer workflow.
• Build and maintain the internal agentic AI platform, including skills catalogs and MCP integrations.
• Define architecture and standards for evaluating, deploying, and securing agents and model releases.
• Improve onboarding, documentation, and discovery layers for tooling adoption.

Skills

AI/LLMs

TypeScript

REST APIs

CI/CD

AWS

Developer tooling

Platform engineering

Cross-functional collaboration

Code generation

Education

Bachelor's degree in CS/Engineering

Tools

AWS

MCP servers

Source control

CI/CD pipelines

LLM frameworks

Job description

About You

You've built tools that engineers rely on. You think agentic AI and developers working together is one of the most interesting opportunities of this decade, and you want your fingerprints on the tools, standards, and platform that make that possible here. You understand the full process of shipping an agent into production: prompting, tool and MCP design, reliability, evals, the UX of human-AI handoffs, and the plumbing in between.

What skills do I need?

• 5+ years of software engineering experience, ideally with a focus on developer tooling, platform engineering, or internal-facing/DevX systems
• Meaningful hands-on experience building with AI/LLMs and shipping agentic solutions. Whether that's a career focus, or a more recent but deep pivot into the space
• Proven ability to build internal tools that make powerful AI capabilities accessible to engineers, including the judgment to know when to build vs. buy, and when to standardize vs. let teams experiment
• A natural collaborator who earns trust with engineers quickly, understands real engineering pain points, and co-creates solutions that get adopted rather than shelved
• Strong full-stack proficiency (TypeScript and related ecosystem), deep familiarity with API design and integration (RESTful services, MCP, and similar), and comfort working across a modern engineering tech stack
• Deep hands-on experience with LLMs, prompt engineering, agent frameworks, RAG, and tool-use/function-calling patterns.
• Production experience with AWS, modern CI/CD practices, and a genuine understanding of AI safety and security, especially around code execution and access to internal systems
• Experience with or strong interest in developer experience fundamentals: reducing friction, measuring engineering productivity, and treating internal tooling like a product with real users
• Bachelor's degree in Computer Science, Engineering, or equivalent work experience

Key Responsibilities

• Partner with engineering teams to identify the highest-leverage AI opportunities in the developer workflow: from code generation and review to testing, debugging, and internal tooling.
• Build and maintain the internal agentic AI platform engineers rely on daily: skills, plugins, MCP servers, and integrations across our tech stack (source control, CI/CD, observability, ticketing, and more)
• Own foundational architecture and standards for how agents and model releases are evaluated, and deployed internally: including reliability, evals, efficiency, and secure tool access patterns
• Build and improve the onboarding, documentation, and discovery layer that helps engineers find and adopt the right AI tools (skills catalogs, guides, internal wikis) rather than reinventing them