Lead Forward Deployed Engineer

Elios AI; Miami (FL); Hybrid; USD 150,000 - 210,000; Full time

Benefits offered by this job

Competitive compensation

Hybrid work setup

Job summary

Elios AI in Miami, FL is seeking a Senior Software Engineer to lead client engagements building production AI systems. You will own delivery from scoping conversations through deployment, staying hands-on with architecture and code while guiding a small engineering team.

You will architect LLM-powered platforms, hybrid RAG pipelines, and cost-aware integrations, present recommendations to stakeholders, and ensure quality through observability and robust testing.

Qualifications

• 7+ years of production software engineering with substantial LLM work.
• Proven track record leading client-facing delivery of shipped projects.
• Deep experience with production AI patterns: retrieval metrics, hallucination mitigation, latency and cost optimization.
• Full-stack capability across Python, TypeScript, React, and modern backend frameworks.
• Able to lead a team while remaining a hands-on technical contributor.

Responsibilities

• Lead delivery of production AI engagements end to end, from scoping through deployment.
• Architect LLM-powered systems: multi-agent platforms, hybrid RAG pipelines, and integrations with cost controls and fallback strategies.
• Present technical recommendations to stakeholders and then deliver on them.
• Guide and review the work of other engineers without stepping out of the code yourself.
• Establish evals, observability, and quality bars so what ships holds up under real usage.
• Direct agentic coding tools (Claude Code, Cursor, Codex) with intent, owning every line that goes out.

Skills

LLM-focused development

Client-facing delivery

Full-stack development

Team leadership

Tools

Claude Code

Cursor

Codex

Job description

Location: Miami, FL | Type: Full Time | Setup: Hybrid | Experience: 7+ years

About the Role

You'll lead client engagements building production AI systems, owning delivery from the first scoping conversation through deployment. You stay hands-on with the architecture and the code while guiding a small team of engineers and serving as the technical voice clients trust.

Our client is an organization putting AI into production at enterprise scale, where engagements succeed on both engineering quality and stakeholder communication. Building the right thing matters as much as building the thing right.

This role is for engineers who lead from the front: still shipping, still reviewing code, still fluent in current tooling, while carrying the client relationship.

What You'll Do

• Lead delivery of production AI engagements end to end, from scoping through deployment
• Architect LLM-powered systems: multi-agent platforms, hybrid RAG pipelines, and integrations with cost controls and fallback strategies
• Present technical recommendations to stakeholders and then deliver on them
• Guide and review the work of other engineers without stepping out of the code yourself
• Establish evals, observability, and quality bars so what ships holds up under real usage
• Direct agentic coding tools (Claude Code, Cursor, Codex) with intent, owning every line that goes out

Qualifications

• 7+ years of production software engineering, including substantial LLM-focused work
• A track record of leading client-facing delivery, with projects that shipped and ran reliably
• Deep experience with production AI patterns: retrieval metrics, hallucination mitigation, latency and cost optimization
• Full-stack capability across Python, TypeScript, React, and modern backend frameworks
• Able to lead a team while remaining a hands-on technical contributor

Why Join Us

You'll own meaningful engagements with real authority over how they're delivered, alongside practitioners who build the same systems daily. Competitive compensation and benefits.