AI Agent & Infrastructure Engineering Intern (Graduates Only)

ELDAEON INC.; Azusa (CA); On-site; USD 23,000 - 32,000; Full time

Benefits offered by this job

Paid housing in Azusa

Direct access to founders

Hands-on hardware projects

Job summary

ELDÆON INC. in Azusa, CA, offers an internship to graduates for building the AI layer of our platform. You will work on agent harnesses, context pipelines, and open-weight model deployment on our own hardware. Strong Python, Linux, and hands-on tool experience are essential, with on-site interview and relocation support as needed.

You will also help design scalable compute infrastructure for distributed NLP workloads and ensure reliable human-in-the-loop safety.

Qualifications

• Completed BS or MS in CS/CE/EE or related field; degree conferred; current students not eligible.
• Strong Python and Linux command line skills.
• Hands-on work with agentic coding tools beyond casual use.
• Solid understanding of LLM API mechanics, including tool calls and context windows.
• Able to build and debug developer tooling; hands-on with hardware.

Responsibilities

• Build agent harnesses and internal tooling to enable reliable agent work.
• Design context pipelines exposing repos, telemetry, dashboards, and Jira/Confluence.
• Implement model routing across Bedrock and OpenRouter with cost/latency awareness.
• Deploy open-weight LLMs on our own hardware and manage the compute stack.
• Define metrics for agent reliability and governance for unsupervised use.

Skills

Python

Linux

Agentic coding tools

LLM API basics

Education

BS or MS in Computer Science, Computer Engineering, Electrical Engineering or related

Tools

Claude Code

Claude Desktop

Codex

Job description

Please note before applying: this internship is open to graduates only (degree conferred; current students are not eligible) and is fully on-site in Azusa, CA, including an in-person interview — candidates should be in the greater Los Angeles area or able to relocate.

This is not a prompt-writing role and it is not an ML-research role. You will build the AI layer our company runs on — agent harnesses, context pipelines, model routing, internal tooling — and the physical compute cluster it runs on. Software and hardware, both.

ABOUT ELDAEON:

ELDÆON is building the world's first tactical UAP-detection network. Our sensor-fusion platform is engineered ground-up to detect what conventional defense systems were never designed to see — anomalous aerial phenomena that violate restricted airspace, including near nuclear facilities and military installations.

Our platform is:

• Modular — adaptable across rooftop, field, and networked regional deployments
• Multimodal — fusing optical, RF, environmental, biometric, and temporal data
• Real-time — live detection, correlation, and characterization of aerial phenomena

We are sensor hackers, reverse engineers, and deep-tech builders. We build what others won't.

THE ROLE:

We run two flagship sensing platforms — DIONYSUS (multi-sensor UAP-detection enclosure) and NEMESIS (passive radar) — across dev units, provisioned field units, and live deployments. They generate a constant stream of bugs, stale data streams, config drift, and integration gaps. Today humans find those bugs and humans fix them.

That's the problem you're here to solve. We want the agents finding and fixing, and engineers reviewing.

We have the beginnings of an internal agent system. What it lacks is the harness, the context, and the reliability to be trusted unsupervised — right now a bad autonomous fix could take down a data pipeline, so we keep a human in the loop on everything. Getting past that trust threshold is the single highest-leverage problem at this company, and it's yours.

You will also build the compute that makes it possible. We're standing up our own inference infrastructure — distributed NVIDIA GB10 nodes and RTX PRO 6000 servers — so we can run open-weight models on our own data without sending it to a third party. You'll rack it, network it, and load models on it.

WHAT YOU'LL DO:

AI systems & software

• Build agent harnesses and internal tooling — the scaffolding that lets agents work our codebase, sensor fleet, and docs reliably instead of one-off prompting
• Design context pipelines that give agents real awareness of ELDÆON: repos, commit history, sensor telemetry, dashboards, Confluence, Discord, and Jira
• Implement model routing across Amazon Bedrock and OpenRouter — pick the right model per task on cost, latency, and capability, with fallback behavior
• Work with agentic coding tools (Claude Code, Codex) as production instruments, not chat toys — loop engineering, evals, guardrails, and PR-gated autonomy
• Deploy and serve open-weight LLMs on our own hardware
• Build internal software for our business and engineering teams — voice-to-text capture, automated triage of sensor and dashboard anomalies, agent-authored PRs that a human approves before merge
• Define how we measure agent reliability, so we can justify expanding what runs unsupervised

AI hardware infrastructure

• Build a distributed compute cluster from multiple NVIDIA GB10 systems — routing, network switching, cabling, and interconnect for pooled VRAM and distributed workloads
• Spec and assemble our own GPU servers around RTX PRO 6000 class cards
• Own the full stack: power, thermals, networking, drivers, orchestration, model loading, monitoring

WHAT WE ARE LOOKING FOR:

Required

• Completed BS or MS in Computer Science, Computer Engineering, Electrical Engineering, or a related discipline (degree already conferred, current students are NOT eligible)
• Strong Python and Linux command line
• Demonstrated hands-on work with agentic coding tools (Claude Code / Claude Desktop / Codex) — beyond casual use; you've built something with them
• Real understanding of LLM API mechanics — tool/function calling, context windows, streaming, token cost, prompt caching
• Comfortable building and debugging your own developer tooling
• Willing and able to work hands-on with physical hardware — racking machines, running cable, configuring switches
• Able to be on-site in Azusa for the full internship

Strongly preferred

• Multi-provider model routing (Amazon Bedrock, OpenRouter, or equivalent) with cost/latency-aware policies
• Serving open-weight LLMs — vLLM, llama.cpp, TensorRT-LLM, Ollama; quantization and VRAM budgeting
• Multi-agent orchestration and long-running agent loops with meaningful evals
• Retrieval / context engineering over heterogeneous internal sources
• GPU infrastructure — CUDA, driver stacks, multi-GPU and multi-node topology, NCCL, InfiniBand or high-speed Ethernet
• Networking fundamentals: VLANs, managed switches, subnetting, DNS, captive portals
• Voice-to-text pipelines (Whisper or similar) integrated into real workflows
• Fine-tuning or adapting open-weight models on proprietary data (LoRA/QLoRA)
• MCP servers, CI/CD, and infrastructure-as-code

Bonus

• You've built your own homelab, GPU rig, or self-hosted inference setup
• Personal projects where agents do real work on a schedule, not in a notebook
• Genuine curiosity about UAP, anomalous aerial phenomena and the frontier of sensing

PERKS:

• Paid — $20/hr, full-time (40 hrs/week)
• Free company-provided housing in Azusa, CA available for select interns (decided at offer stage; based on candidate strength and need)
• Real ownership — you own the AI layer the whole company runs on, not a throwaway intern project
• Serious hardware — you build and keep your hands on GB10 and RTX PRO 6000 class compute
• Direct access to founders and senior engineers
• Frontier work — the platform you'll build doesn't have a textbook

ELDÆON develops technology subject to U.S. export-control regulations, including the International Traffic in Arms Regulations (ITAR) administered by the U.S. Department of State's Directorate of Defense Trade Controls (DDTC).

• Radar-related work is restricted to U.S. Persons. Core radar signal processing, NEMESIS passive-radar firmware, and any related controlled technical data may only be accessed by U.S. Persons as defined under 22 CFR §120.62 (U.S. citizens, U.S. lawful permanent residents, and protected individuals under 8 U.S.C. §1324b(a)(3)).
• Non-U.S. Persons remain eligible for this role and may work on ancillary, non-controlled scope including AI infrastructure, internal tooling, model serving, compute cluster buildout, and non-radar data pipelines.
• Final scope assignment is made at offer stage based on applicant status and current export-control posture.

We evaluate every qualified applicant on the merits and structure scope around compliance — citizenship is not a disqualifier for the role itself.

ELDÆON is an equal-opportunity employer. We build what others won't — and we hire people who do the same.