via Greenhouse
$90K - 150K a year
Design, build, and operate AI agents and retrieval context layers ensuring cost, latency, security, and reliability in production AI systems.
6+ years software development, 1+ year shipping LLM-powered features, proficiency in Python, TypeScript, or Ruby, cloud platform and retrieval system experience, bachelor's degree.
Senior Software Engineer, AI Platform (Remote) Overview: Weedmaps is hiring a Senior Software Engineer to build the AI systems our company runs on: the agents that do real engineering and operational work, and the "AI brain" that gives them trustworthy context about our business. You will work on an autonomous coding agent that picks up Jira tickets, opens pull requests and responds to review feedback; a shared platform (an internal MCP server) that gives every agent common skills, tools and processes; and a knowledge layer that connects our Snowflake semantic layer, internal documentation and a growing knowledge graph so agents and people get consistent answers. Success means agents that are measurably useful, cheap enough to run at scale, and safe to trust with production systems. This role sits on the AI Platform team and partners closely with Developer Experience, Data and product engineering teams across the company. The impact you'll make: Design, build and operate production AI agents, including an autonomous coding agent that works from Jira and Slack, opens PRs, fixes its own CI failures and applies review feedback. Build the retrieval and context layer behind our "AI brain": embeddings and semantic search, knowledge-graph modeling, and integration with our Snowflake semantic layer and internal docs, so agents pull the right context in one pass instead of several. Extend our internal MCP server with shared skills, tools and processes that other teams can reuse, and help product teams bring agents into their own workflows. Own evaluation: build offline test sets and online metrics that show whether a change to a prompt, model or retrieval step made an agent better or worse, and gate releases on them. Drive cost and latency down: route work to the cheapest model that can do it, use caching and structured outputs, and track spend per agent and per task on AWS Bedrock. Harden agents against prompt injection, memory poisoning and over-broad permissions: least-privilege tool access, auditable actions, human approval where the risk warrants it. Instrument agents with tracing and logging so failures can be diagnosed and fixed quickly, and take part in on-call for the systems you own. Evaluate new models and tools with a practical eye, adopting what holds up and passing on what doesn't. Write clear design docs, review code, and mentor other engineers on building with LLMs. What you've accomplished: Bachelor's degree or equivalent practical experience. Minimum of 6 years of professional software development experience, including owning production services end to end. At least 1 year of hands-on experience shipping LLM-powered features or agents to production (not only prototypes): tool/function calling, prompt design, structured outputs, and handling model failures gracefully. Experience building retrieval systems: embeddings, vector or hybrid search, chunking and ranking, and measuring retrieval quality. Strong proficiency in at least one of Python, TypeScript or Ruby, and comfort working across a polyglot codebase. Experience with a major cloud platform (AWS preferred), CI/CD, and observability tooling. A track record of measuring what you build: evals, A/B tests or clear before/after metrics. Bonus points: AWS Bedrock, and experience managing model cost and latency at scale. Model Context Protocol (MCP) servers or other agent tool frameworks. Knowledge graphs or semantic layers (for example, Snowflake semantic views, dbt metrics or graph databases). Agents that act on developer workflows: GitHub Actions, Jira and Slack integrations, automated code review or code generation. LLM security: prompt-injection defenses, sandboxing, permission models and red-teaming. Entity matching or classification at large scale (millions of records) using ML combined with LLM reasoning. Experience with Ruby on Rails, Elixir or Node.js services. Experience at a marketplace, e-commerce or regulated-industry company. The base pay range for this position is $196,984.00 - $222,000.00 per year, and a competitive bonus 2026 US Benefits for Full Time, Regular Employees: Physical Health (Medical, Dental & Vision) 100% employer-paid premium for employees Up to 80% coverage for dependents Company HSA contribution with the High Deductible Health Plan 401(k) Retirement Plan (employer will match contribution up to 3.5% of employee contribution) Basic Life, Voluntary Life and AD&D Insurance options Supplemental, voluntary benefits Student Loan Repayment/529 Education Savings with a monthly company contribution FSA (Medical, Dependent, Transit and Parking) Voluntary Life and AD&D Insurance Critical Illness Insurance Accident Insurance Short- and Long-term Disability Insurance Pet Insurance Identity theft protection Legal access to a network of attorneys PTO, paid sick leave, and company holidays (including a 2026 holiday shutdown) Paid parental leave Why Work at Weedmaps? Life at Weedmaps means innovation and heart. Come join us if you care about the plant, the people who love it, and are ready to let your talent shine. We foster a bustling and collaborative culture that revolves around an environment that focuses on the benefits of weed, and the community that supports it. You too can have a hand in shaping the industry’s future; ready to roll with us? See how we’ve grown—our journey, leadership team, and what’s next at Weedmaps.com/corporate About Weedmaps: Founded in 2008, we’ve grown from a small startup to a global leader in the cannabis industry. Our dedication to transparency, education, and community has set us apart, and today, we proudly serve cannabis to consumers and businesses in the U.S. and worldwide. “Freedom to choose. Freedom to access. Freedom to enjoy.” Notice to prospective Weedmaps job applicants: Our team has been made aware of incidents involving LinkedIn, Telegram, and Facebook accounts impersonating Weedmaps recruiters. These individuals are attempting to use our company name to solicit payment from prospective candidates interested in applying for jobs at our company. Our team is actively working to combat these attempts, but in the meantime, please be mindful of the following: Our recruiters will always communicate with candidates through an @weedmaps.com email address. CORRECT: jlebowski@weedmaps.com INCORRECT: jlebowski@gmail.com Our recruiters will NEVER ask for or attempt to solicit payment from applicants in order to apply, interview, or work for Weedmaps. If you are interested in a role at Weedmaps, please apply through our established channels. Weedmaps Careers Page or LinkedIn If you are unsure if a communication is legitimate, please contact our recruitment team at talentops@weedmaps.com and they will happily confirm for you. Thank you for your vigilance and we appreciate your interest in working with us! Weedmaps is an equal opportunity employer and makes employment decisions on the basis of merit. The Company prohibits unlawful discrimination against employees or applicants based on race (including traits historically associated with race, such as hair texture and protective hairstyles), religion and religious creed, color, national origin, ancestry, physical disability, mental disability, medical condition, genetic information, marital status, sex, gender, gender identity, gender expression, age, military status, veteran status, uniformed service member status, sexual orientation, transgender identity, citizenship status, pregnancy, or any other consideration made unlawful by federal, state, or local laws. The Company also prohibits unlawful discrimination based on the perception that anyone has any of those characteristics, or is associated with a person who has or is perceived as having any of those characteristics. Our company uses E-Verify to confirm the employment eligibility of all newly hired employees. To learn more about E-Verify, including your rights and responsibilities, please visit www.dhs.gov/E-Verify. Applicants are entitled to reasonable accommodations under the terms of the Americans with Disabilities Act and applicable state/local laws, unless the accommodation presents undue hardship. Please email us at peopleoperations at weedmaps.com if you would like to confidentially discuss a potential accommodation during the interview process.
This job posting was last updated on 10/5/2026