4+ years of experience in building production software, particularly with LLM or ML-powered products.
Proven track record of shipping agentic systems beyond prototypes, utilizing production feedback for improvements.
Strong programming skills in Python and/or TypeScript, including APIs, tests, and data modeling.
Experience with tool calling, structured generation, and multi-step workflows.
Ability to make sound judgments on model usage versus deterministic code or human intervention.
Comfortable debugging nondeterministic behavior and identifying reproducible failure modes.
Demonstrated high agency and effective communication skills, especially in dynamic environments.
Responsibilities
Design and deploy production agents that handle planning, context retrieval, tool usage, and multi-step tasks.
Develop orchestration patterns for specialized agents, focusing on task decomposition and delegation.
Create evaluation suites to assess task success, factuality, and cost-effectiveness.
Enhance context engineering across various data types and the Echelon ontology.
Establish guardrails for permissions, data sensitivity, and model output reliability.
Analyze models and prompting strategies using production data rather than intuition.
Collaborate with Product Engineering and domain experts to translate BizOps workflows into agent capabilities.
Benefits
Team lunches and dinners in the office.
On-site gym access for all employees.
Fully covered health, dental, and vision insurance.
401(k) plan.
Access to AI tooling of your choice.
Unlimited PTO.
Full Job Description
The mandate
Build the agent architecture that turns enterprise context into reliable action. You will design agent loops, tool-use patterns, evaluation systems, and multi-agent coordination that work on ambiguous, high-stakes operational problems rather than controlled demos.
What you'll own
Design and ship production agents that plan, retrieve context, call tools, generate artifacts, and complete multi-step work.
Build orchestration patterns for specialized agents and agent swarms, including task decomposition, delegation, shared state, recovery, and human approval.
Create evaluation suites for task success, factuality, tool selection, safety, latency, and cost.
Improve context engineering across prompts, retrieval, memory, structured state, documents, and the Echelon ontology.
Build guardrails for permissions, tenant isolation, sensitive data, unsafe actions, and unreliable model output.
Compare models and prompting strategies with production traces and measured outcomes rather than intuition.
Partner with Product Engineering and domain experts to turn real BizOps workflows into dependable agent capabilities.
Own failures in production and improve the architecture until the same class of failure cannot recur.
What you bring
4+ years building production software, including substantial hands-on work with LLM or ML-powered products.
Evidence that you have shipped an agentic system beyond a prototype and improved it using production feedback or evaluations.
Strong Python and/or TypeScript engineering, including APIs, tests, data modeling, asynchronous work, and observability.
Experience with tool calling, structured generation, retrieval, model evaluation, and multi-step workflows.
Strong judgment about when to use a model, deterministic code, a human checkpoint, or a simpler product interaction.
Comfort debugging nondeterministic behavior and reducing it to measurable, reproducible failure modes.
High agency, direct communication, and comfort owning outcomes under changing requirements.
Useful experience
Multi-agent systems, long-running agents, computer use, code execution, or planning and reasoning systems.
Vercel AI SDK, OpenAI, Anthropic, Mistral, AI Gateway, Braintrust, or comparable platforms.
Knowledge graphs, ontologies, process mining, entity resolution, or temporal data.
