Senior AI/ML Engineer

About the Role

Join an applied AI team building the production systems behind an enterprise process intelligence platform. You will turn complex customer data into reliable, useful product experiences powered by hosted frontier models.

What You'll Do

• Own customer-facing AI features end to end, from technical design and implementation through deployment, monitoring, and ongoing improvement.

• Build Python services and pipelines for retrieval, context construction, model and provider selection, structured extraction, orchestration, and monitoring.

• Develop evaluations, representative datasets, benchmarks, regression tests, and launch gates to measure and improve AI quality.

• Make AI systems resilient to latency, cost, provider errors, and unreliable intermediate outputs using retries, guardrails, verification, and fallbacks.

• Improve retrieval and knowledge workflows, including embeddings, hybrid search, chunking, ranking, and reranking.

• Use customer feedback and production observations to identify issues, run experiments, and ship product improvements.

What We're Looking For

• Four to ten years of applied AI, ML, or production software engineering experience, including sustained ownership of customer-facing systems.

• Strong Python experience, familiarity with Go and typed languages, and experience building asynchronous services.

• Hands-on experience with hosted LLM APIs, RAG or retrieval, agent orchestration, structured outputs, and production AI evaluations.

• Experience building reliable, observable AI services, benchmarks, guardrails, and CI/CD workflows, with a track record of shipping to external customers.

• Ability to reason across the full pipeline from raw enterprise data to generated outputs and user-facing product behavior.

• Experience in a startup or other fast-moving product environment, working directly with customers and iterating from feedback.

• A bachelor's degree or higher in computer science, engineering, or a related technical field.

• Experience with PostgreSQL, Redis, React, TypeScript, GCP, Terraform, Docker, Datadog, and AI tools or services such as OpenAI, Anthropic, Gemini, and Cohere is relevant.

• Document understanding, multimodal data, or enterprise workflow experience is a plus.

Compensation & Benefits

Visa sponsorship is available.

Location

On-site, five days per week in San Francisco, California.