Lead AI Engineer, LLM & Agent Systems (Remote)

BNB Chain; United States; Remote; USD 180,000 - 240,000; Full time

Benefits offered by this job

Fully remote

Flexible working hours

Global organization with international

Competitive salary and benefits

Job summary

Trust Wallet is seeking a Lead AI Engineer to own the backend and Agent systems behind our LLM-powered products. You will build the Agent workflows, define quality metrics, keep them reliable in production, and shape the product's future.

This role requires shipping LLM features to real users, maintaining them with data-driven improvements, and working across a fully remote, global team.

Qualifications

• Production LLM/Agent features used by 10,000+ active users and maintained after launch.
• Strong backend engineering fundamentals with production APIs and data flows.
• Real evaluation discipline with regression tests and production monitoring.
• Ownership mindset: decisions, risk surfacing, verified production readiness.
• Web3 experience: crypto/DeFi experience preferred.

Responsibilities

• Build and own AI backend and Agent workflows for multi-turn conversations, tool calls, and retrieval.
• Define success metrics with Product, Design, and QA; turn failures into evaluation samples.
• Diagnose root causes across the stack: model judgments, tool responses, backend issues.
• Ensure production reliability: timeouts, retries, degradation, asynchronous jobs, dependencies.
• Shape product/tech decisions with feasible, cost-aware alternatives; break work into phased deliverables.
• Communicate progress, blockers, and ETAs; provide thorough handover materials after launch.

Skills

LLM/Agent experience

Backend engineering

Evaluation discipline

Ownership mindset

Web3 experience

Tools

Golang

Job description

Trust Wallet is seeking a Lead AI Engineer to own the backend and Agent systems behind our LLM-powered products. You will build the Agent workflows, define quality metrics, keep them reliable in production, and shape the product's future.

This role requires shipping LLM features to real users, maintaining them with data-driven improvements, and working across a fully remote, global team.