AI Engineer

thesiscareers; New York (NY); On-site; USD 140,000 - 190,000; Full time

Job summary

Thesis is seeking an AI Engineer to build agents, integrations, and internal tools that help a small team accomplish more. You'll work with Data, Engineering, Growth, Creative, and Operations to identify valuable problems, prototype solutions, and own them through deployment, adoption, and ongoing improvement.

This is a hands-on software engineering role focused on applied AI. You'll build with existing models, connect them to our tools and knowledge, and make outputs useful and trustworthy,

Qualifications

• Hands-on experience building and deploying AI-powered workflows.

Responsibilities

• Build agents that perform multi-step tasks and retrieve information across business systems.
• Integrate workflows via APIs and tools like Slack, Google Workspace, Asana, Shopify, and Klaviyo.
• Extend and reuse company knowledge retrieval and context-management systems.

Skills

Python

TypeScript

LLM application development

APIs

SQL

Data validation

Asynchronous jobs

Tools

Anthropic API

OpenAI API

Slack API

Google Workspace API

Asana API

Shopify API

Klaviyo API

Job description

About Us

At Thesis, we believe everyone should have the opportunity to meet their potential. We build nootropic supplements and customer experiences that help people find the right support for their goals.

Across Thesis and Stasis, we're also changing how our company works. Our teams use AI to develop creative, research customers, build digital experiences, analyze performance, and reduce repetitive operational work. We're looking for an engineer who can turn those experiments into reliable systems that people use every day.

About the Role

We're looking for an AI Engineer to build the agents, integrations, and internal tools that help a small team accomplish more. You'll work with Data, Engineering, Growth, Creative, and Operations to find valuable problems, prototype solutions, and own them through deployment, adoption, and ongoing improvement.

This is a hands‑on software engineering role focused on applied AI. You'll build with existing models, connect them to our tools and knowledge, and make their outputs useful and trustworthy. You should be as comfortable debugging an API integration as designing an agent workflow, and care about whether your work saves time, improves decisions, or helps the business grow.

We already have AI-assisted workflows and a shared Claude skill and knowledge system. You'll build on that foundation, making successful workflows easier to reuse and bringing production engineering to the parts that need it. You won't be starting from a blank page, and you won't be limited to maintaining what's already there.

How You'll Make an Impact

Build agents that do useful work

• Design and ship agents that retrieve information, use tools, and complete multi‑step tasks across our business systems.
• Connect workflows across tools such as Slack, Google Workspace, Asana, Shopify, and Klaviyo through APIs, webhooks, and MCP integrations.
• Make long‑running workflows dependable with persistent state, retries, duplicate prevention, clear approvals, and recoverable failures.

Accelerate creative and growth workflows

• Partner with Creative and Growth to improve the path from customer research and performance insights to briefs, scripts, creative variants, and testable landing pages.
• Build workflows that combine brand knowledge, approved product claims, asset libraries, and creative performance data while keeping human review where it matters.
• Help teams learn from prior experiments so each new brief or test benefits from what we've already discovered.

Make company knowledge and data more useful

• Extend our shared skills, knowledge base, retrieval, and context‑management systems so AI tools can find and use the right source material.
• Partner with our data team to connect AI workflows to governed analytics in Metabase and Hex, backed by Snowflake, rather than inventing competing definitions of business metrics.
• Use SQL and data validation to investigate issues, verify outputs, and make analytical workflows easier for non‑technical teammates to use.

Turn prototypes into reliable products

• Build evaluations using real business tasks. Test accuracy, task completion, tool behavior, failure recovery, latency, and cost before scaling a workflow.
• Add monitoring, useful logs, version control, automated tests, and clear documentation. Own failures after launch and fix their causes.
• Protect customer and company data, separate brand and account contexts, and preserve human approval for consequential actions.
• Choose the simplest approach that works, including ordinary code or deterministic automation when an LLM adds no value.

Help the company use AI well

• Work directly with teammates to understand their workflows, ship usable interfaces, and help them adopt what you build.
• Create reusable skills and integrations rather than isolated prompts that only their author can operate.
• Evaluate new models and tools through practical experiments, then explain what is worth adopting and why.
• Measure outcomes such as time saved, adoption, output quality, and faster experiment cycles, not just the number of automations shipped.

We’re Excited About Your

• Experience shipping software that real users depend on, with ownership beyond the initial prototype.
• Hands‑on LLM application development using Anthropic, OpenAI, or comparable APIs, including structured outputs, tool calling, retrieval, and multi‑step workflows.
• Strong Python or TypeScript skills, sound software design, and comfort working with APIs, authentication, databases, and asynchronous jobs.
• Practical understanding of RAG, context management, and MCP. You can explain the trade‑offs and show when a simpler approach is better.
• Ability to build evaluations, diagnose unreliable behavior, and improve an AI system using evidence rather than prompt tweaking alone.
• Working SQL proficiency and experience validating data against established reporting or warehouse models.
• Product judgment and clear communication. You can turn an ambiguous request into a