1 month ago
Remote, United StatesSenior
Base Salary
$197k - $222k/yr
Responsibilities
- Design, build, and operate production AI agents, including an autonomous coding agent that works with Jira and Slack, opens pull requests, fixes CI failures, and applies review feedback.
- Build retrieval and context systems using embeddings, semantic search, knowledge-graph modeling, Snowflake semantic data, and internal documentation.
- Extend the internal Model Context Protocol server with reusable skills, tools, and processes.
- Create offline test sets and online metrics to evaluate prompts, models, retrieval, and agent performance, and gate releases on evaluation results.
- Reduce model cost and latency through model routing, caching, structured outputs, and spend tracking on AWS Bedrock.
- Harden agents against prompt injection, memory poisoning, and excessive permissions using least-privilege access, auditable actions, and human approval workflows.
- Instrument systems with tracing and logging, participate in on-call for owned systems, evaluate new models and tools, write design documents, review code, and mentor engineers.
Requirements
- Bachelor’s degree or equivalent practical experience.
- At least 6 years of professional software development experience, including end-to-end ownership of production services.
- At least 1 year of hands-on experience shipping LLM-powered features or agents to production, including tool or function calling, prompt design, structured outputs, and model-failure handling.
- Experience building retrieval systems with embeddings, vector or hybrid search, chunking, ranking, and retrieval-quality measurement.
- Strong proficiency in at least one of Python, TypeScript, or Ruby, with comfort working across a polyglot codebase.
- Experience with a major cloud platform, with AWS preferred, and with observability tooling.
- A record of measuring software outcomes through evaluations, A/B tests, or clear before-and-after metrics.
- Preferred experience includes AWS Bedrock, Model Context Protocol servers, knowledge graphs, semantic layers, GitHub Actions, Jira, Slack integrations, automated code review or code generation, LLM security, sandboxing, permission models, red-teaming, large-scale entity matching or classification, Ruby on Rails, Elixir, Node.js, or work in marketplace, e-commerce, or regulated-industry companies.
Benefits
- Remote role with full-time regular employee benefits.
- Medical, dental, and vision coverage with 100% employer-paid employee premiums and up to 80% dependent coverage.
- Company HSA contribution with the High Deductible Health Plan and a 401(k) match of up to 3.5% of employee contribution.
- Life, AD&D, disability, critical illness, accident, pet, identity theft protection, legal access, FSA, transit and parking, and supplemental voluntary benefits.
- Student loan repayment or 529 education savings support through a monthly company contribution.
- PTO, paid sick leave, company holidays including a 2026 holiday shutdown, and paid parental leave.
Tech Stack
Categories
About Weedmaps
Weedmaps builds an online marketplace and software suite for cannabis consumers, dispensaries, and brands. Consumers use its site and app to find licensed retailers, products, menus, and delivery, while businesses buy advertising and SaaS tools for listings, orders, and compliance. Founded in 2008 and headquartered in Orange County, CA, Weedmaps is a NASDAQ-listed public company (WM Technology, Inc.).