Senior AI Engineer
External
Raylu-ai · New York City$165K–$230K/yrFull-timeOn-site4mo ago
LessLLMsRouting
Prepare for this interview
EliteAI-generated questions, company research, and talking points tailored to this role
Responsibilities
- Design, build, and productionize agent workflows end-to-end (APIs, tools, evals, monitoring).
- Create safety, cost, and latency controls; build dashboards and alerts for reliability.
- Partner with product/design to invent new interaction patterns and ship them fast.
- Document patterns and mentor engineers on best practices for LLM-powered features.
Requirements
- Agentic systems : Function/tool calling, multi-step planning, routing, memory, and retrieval.
- Engineering first : You can wire up services, craft eval harnesses, and debug latency/cost at scale.
- LLM breadth : Comfortable comparing models/hosts, prompt strategies, and guardrail techniques.
- Product focus : You instrument outcomes, run A/Bs, and iterate to improve task success rates.
- Opinionated: Deep level of understanding of the technological landscape, making both high level system and granular code design decisions based on understanding rather than preference - diving deep on unknown patterns in order to build the best product.
- Experience with workflow engines (e.g., Temporal), comfort in full stack engineering
- Logistics :
- Compensation: $165K - $230K salary, competitive equity (4 year vest)
- Location: New York City. We are a fully in-office team working out of Midtown Manhattan Monday through Friday. We allow for WFH days when anyone is traveling, but we do not allow for permanent remote work.
Benefits
Generous health, dental, and vision insurance401k with 3% automatic contribution (no vesting)Paid LunchesWellness and Citi Bike benefitUnlimited PTOHealth insuranceDental insuranceVision insurance401(k)Paid time offRemote work optionsEquity / stock options
Additional Information
Position Summary We're hiring a product-oriented Senior AI Engineer who loves tinkering with LLMs and shipping real agent systems. We spend less time on fine-tuning and more on orchestration, evaluation, and reliability-so agents do real work safely, quickly, and repeatedly.
Your Match
How well this role fits your profile.
Company Intel
What employees say
Worked at raylu-ai? Share your experience