Senior AI/ML Engineer

About the Role

This is a senior applied AI engineering role focused on building the AI systems layer behind a B2B process intelligence platform. You will own the pipelines that turn messy enterprise data into structured, reliable intelligence, working directly with frontier model APIs from providers like OpenAI, Anthropic, and others. The work spans retrieval, context construction, structured extraction, evaluation, orchestration, and production monitoring.

What You'll Do

• Design and maintain production AI pipelines covering retrieval, context assembly, model and provider selection, and structured output extraction.

• Define what "good" looks like for AI outputs, build representative evaluation datasets, and ship regression tests, guardrails, and fallback paths.

• Build and iterate on RAG systems, hybrid search, chunking, ranking, and reranking to surface useful context from messy knowledge sources.

• Make multi-step, tool-using agentic workflows reliable when plans, tools, or intermediate outputs can fail.

• Extract structured, trustworthy information from long or complex enterprise documents, including multimodal inputs.

• Monitor production AI behavior for latency, cost, failures, and quality drift, and drive improvements based on data.

• Communicate directly with customers to gather feedback and iterate on AI features accordingly.

What We're Looking For

• 4 or more years of experience building and shipping production AI/ML or applied software systems, with sustained end-to-end ownership.

• Expert-level Python, including async patterns and integration with AI/ML tooling; familiarity with a typed language (Go, C++, Java, or similar) is a plus.

• Proven experience building evals, benchmarks, or CI/CD pipelines for AI/ML systems, including LLM-as-judge, golden datasets, and launch gates.

• Hands-on experience with RAG, vector search, embeddings, and agent orchestration systems.

• Strong systems thinking: able to reason end-to-end from raw customer data to generated outputs and user-facing product behavior.

• Experience across multiple ML domains rather than a narrow single-domain specialty.

• Clear written and verbal communicator, comfortable engaging directly with users and customers.

• Startup experience or a genuine affinity for early-stage environments.

• BS or higher in Computer Science, Engineering, or a related technical field.

• Familiarity with multimodal inputs such as documents, screenshots, video, or transcripts is a plus.

• Experience with process mining, task mining, or enterprise workflow tooling is a plus.

Compensation & Benefits

Salary range: $180,000 to $275,000 USD annually. Visa sponsorship is not available for this role.

Location

On-site, five days per week in San Francisco, California. Candidates must already be located in San Francisco.