AI Engineer - NYC
Build production-grade AI infrastructure and agentic systems for a revenue automation platform. Own end-to-end features from ideation through reliable deployment for business-critical finance workflows.
About the job
What you'll be doing
- Build and own AI infrastructure for reliable software on non-deterministic models, including agentic workflows, prompt iteration, tools, and evals
- Develop AI-powered approval workflows: flexible routing configured in natural language that converts to deterministic, auditable business logic
- Create an intelligent collections agent: instruct in natural language to run workflows autonomously, collect context, and handle payments
Requirements
- Shipped LLM-based systems to real customers with first-hand production failure experience
- Designed agentic systems (embeddings, memory, tool use, long-running state, recovery from partial failures)
- Built evals infrastructure (datasets, LLM as judge, prompt regression tests, monitoring)
- Comfortable writing resilient software for business-critical systems on non-deterministic models
- Informed opinions on tooling for building, evaluating, and securely running multi-provider AI systems in production
- Shipped production backend systems with focus on reliability
- Care about customers and thrive in ambiguity
Nice to have
- Experience with Kotlin, Postgres, BigQuery, Vertex AI, LangSmith, Google Cloud, Terraform, TypeScript, React
- Interest in AI security and treating models as untrusted by default
Compensation & Benefits
- Salary: $210,000 - $230,000
- Equity: meaningful share options
- 20 days vacation + national holidays
- Competitive healthcare and 401K
- Visa sponsorship available
Skills
Llm Systems, Agentic Workflows, Evaluations Infrastructure, Kotlin, Postgres, Vertex Ai, Langsmith, GCP, TypeScript, React
Similar jobs
ML Engineering jobs
Firecrawl
San Francisco, CA
Build and operate production machine-learning systems for search ranking, relevance, extraction quality, and LLM-driven features. The role requires production ML ownership, ranking or relevance expertise, large-scale data experience, Python, and rigorous experimentation skills.
Applied Intuition
Sunnyvale, CA
Optimizes distributed machine learning training and high-throughput offline inference across large accelerator clusters. The role focuses on profiling, scaling efficiency, cluster goodput, GPU performance, and cost-effective processing of autonomy data.
ClickUp
United States
Build and operate large-scale ranking and retrieval systems that power search relevance, including hybrid lexical/vector search, embeddings, query understanding, and permission-aware retrieval. Requires a bachelor's degree and 5+ years of ML engineering experience in ranking or information retrieval.
Atomicmachines
Emeryville, CA
Build and operate production ML infrastructure spanning training, deployment, serving, monitoring, data pipelines, and feedback-driven retraining. The role requires strong MLOps and DevOps experience, Python and SQL proficiency, and ownership of reliable cloud-based systems.
Cinder
New York, NY
Build and operate production machine-learning systems for content safety, from messy customer data through classification, evaluation, and inference. The role requires 5+ years of ML engineering experience, strong Python and MLOps skills, and sound judgment across classical models and LLMs.