Senior Forward Deployed Engineer

Elios AI; Miami (FL); Hybrid; USD 120,000 - 180,000; Full time

Job summary

Elios AI is seeking an experienced software engineer to build production AI systems for enterprise clients in a hybrid, Miami-based setting. You will own RAG pipelines, agent workflows, and LLM integrations, delivering measurable outcomes for real users.

The role requires hands-on work with Python, TypeScript, React, and modern backend frameworks, plus direct client interaction to explain decisions and drive outcomes. 5+ years of experience is expected.

Qualifications

• 5+ years of production software engineering, with hands-on LLM-focused work.
• Experience shipping AI systems used by real clients with measurable outcomes.
• Full-stack capability across Python, TypeScript, React, and modern backend frameworks.

Responsibilities

• Build and ship LLM-powered features into production, including RAG pipelines, agent workflows, and model integrations.
• Instrument what you build with evals, observability, latency optimization, and cost management.
• Work directly with client stakeholders, translating technical decisions for non-technical audiences.
• Own your workstream from scoping through deployment.
• Use agentic coding tools daily to amplify output while owning every line that ships.
• Stay current with frameworks, protocols, and models as tooling evolves.

Skills

LLM-focused development

Python

TypeScript

React

Client-facing delivery

Tools

Claude Code

Cursor

Codex

Job description

Location: Miami, FL | Type: Full Time | Setup: Hybrid | Experience: 5+ years

About the Role

You'll build production AI systems for enterprise clients and sit in the room where the decisions get made. This is hands-on engineering work: RAG pipelines with real retrieval metrics, agent architectures with observability, LLM integrations with cost controls and fallback strategies. You ship things real users depend on, then stand behind them with the client.

Our client is a fast-moving organization deploying AI into production environments where the difference between a demo and a product actually matters. The work rewards engineers who are in the trenches with current tooling, not coasting on last year's knowledge.

If you can build the thing right and explain to a stakeholder why it was the right thing to build, this role will fit.

What You'll Do

• Build and ship LLM-powered features into production, including RAG pipelines, agent workflows, and model integrations
• Instrument what you build with evals, observability, latency optimization, and cost management
• Work directly with client stakeholders, translating technical decisions for non-technical audiences
• Own your workstream from scoping through deployment
• Use agentic coding tools (Claude Code, Cursor, Codex) daily to amplify your output while reviewing and owning every line that ships
• Stay current with frameworks, protocols, and models as the tooling landscape moves

Qualifications

• 5+ years of production software engineering, with hands-on LLM-focused work
• Experience shipping AI systems real users depend on, with measurable outcomes
• Full-stack capability across Python, TypeScript, React, and modern backend frameworks
• Client-facing or consulting delivery experience, with a track record of projects that shipped rather than just started
• Comfortable getting hands-on; this is a builder role, not a delegator role

Why Join Us

You'll work on consequential AI deployments with senior practitioners who hold a high bar, with direct client exposure and real ownership. Competitive compensation and benefits.