Role overview
- Employment type: Full-time
- Base salary: $200,000-$260,000 annually
- Experience: 3+ years in ML, data science, or software engineering
- Focus: Backend systems, autonomous agents, and model-layer development
What you will build
- Take ambiguous problems from research and experimentation through prototyping, production deployment, and platform integration.
- Design agent-powered features for root-cause analysis, incident triage, and monitor generation.
- Build evaluation infrastructure, including golden datasets, regression suites, offline and online scoring, and clear quality criteria.
- Own retrieval and context pipelines across customer metadata, data lineage, and query history.
- Monitor production agent behavior through traces, failure classifications, and cost and latency budgets.
- Partner with data science on detection quality and experiment design, and with product management on agent capabilities and boundaries.
- Develop reusable LLM patterns, guardrails, and internal tools for other engineers.
- Evaluate approaches quickly, discontinue unsuccessful experiments, and bring proven solutions into production.
Experience needed
- Hands-on experience building and operating autonomous agents used by real customers, including tool use, internal reasoning loops, and model-directed actions.
- Ownership of an agent evaluation framework with golden datasets, regression testing, and offline and online scoring.
- Experience monitoring agents after launch and addressing issues under production traffic.
- Strong Python and backend engineering skills, supported by an ML or data science background.
- At least three years of experience in ML, data science, or software engineering at startups, AI-native teams, or fast-growing product companies with frequent releases.
- Ability to turn an open-ended problem into an experiment, build a small testable version, and develop successful approaches into production features.
- Daily use of AI tools for coding and research.
- Sound judgment about delivery speed, technical depth, and production reliability.
Additional strengths
- Applied statistics and hypothesis testing.
- Experience building and maintaining MCP servers.
- Experience with data and cloud technologies such as Snowflake, Databricks, dbt, and Airflow.
Benefits and rewards
- Stock options.
- Healthcare plans.
- 401(k) retirement plan.
- Wellness and home office stipends.
- Cell phone or Wi-Fi reimbursement.
- Paid parental leave and flexible time off.
- Generous travel policy.