US Remote AI Engineer: Build Next-Gen Conversational Agents

Point11; Miami (FL); Hybrid; USD 140,000 - 210,000; Full time

Benefits offered by this job

Remote work (US)

Annual learning budget

Job summary

Point11 is building the agents and model pipelines that power the next wave of customer conversations. This remote US role with regular time in Miami focuses on shipping end-to-end LLM-powered features, from prompts and retrieval to tool use and evaluations.

You will design evals, choose models based on cost and latency, and instrument systems to understand outcomes. Ideal candidates think in terms of retries, timeouts, and failures while collaborating with product and Forward Deployed Engineers.

Qualifications

• You’ve shipped LLM-powered features to real users.
• You trust evals and design them into products.
• You think in systems: retries, timeouts, costs, and failure modes.

Responsibilities

• Build the eval suite that tracks agent performance daily.
• Cut latency of Voice/LMM turns while preserving quality.
• Design agents that translate campaign findings into actions.
• Instrument interactions to audit what and why.
• Collaborate with product and Forward Deployed Engineers on requirements.

Skills

LLM features

Eval design

System thinking

Latency optimization

Cross-functional collaboration

Tools

TypeScript

Python

Job description

Point11 is building the agents and model pipelines that power the next wave of customer conversations. This remote US role with regular time in Miami focuses on shipping end-to-end LLM-powered features, from prompts and retrieval to tool use and evaluations.

You will design evals, choose models based on cost and latency, and instrument systems to understand outcomes. Ideal candidates think in terms of retries, timeouts, and failures while collaborating with product and Forward Deployed Engineers.