AI Agent Orchestrator & Verification Engineer

Praxis, Inc.; Torrance (CA); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

Health insurance

Relocation assistance

Equity in startup

Professional development stipend

Unlimited PTO

Job summary

Pronoia Energy in Torrance, CA seeks an AI Engineer to build an agent orchestration framework and a verification harness. You will stand up a self‑hosted open‑weights model on local hardware, and design grounding mechanisms that ensure all claims come from sources or deterministic computation.

You will lead an end‑to‑end loop, routing retrieval and tools, while wearing multiple hats as a founding generalist. Onsite role with strong focus on robustness and rapid iteration.

Qualifications

• A track record shipping a real agent or tool‑use system in production.
• Genuine experience self‑hosting open‑weights models on your own GPUs.
• A habit of treating hallucination and tool‑misuse as engineering problems with mechanical fixes.
• Builder-generalist range across orchestration, model serving, and evaluation.
• A self‑starter who thrives amid ambiguity and rapid iteration.

Responsibilities

• Build the agent orchestrator and the tool‑routing logic at the heart of the system.
• Stand up and serve a self‑hosted open‑weights model on local hardware.
• Build the first verification gate and evaluation harness, making grounding mechanical rather than hopeful.
• Enforce strict routing so claims trace to a retrieved source or a deterministic computation.
• Wear several hats as a founding generalist and later hand specialties to dedicated hires.

Skills

Agent/tool‑use systems

Self-hosting GPUs

Grounding and verification

Orchestration

Model serving

Evaluation harness

Ambiguity handling

Engineering discipline

Education

Physics background

Tools

vLLM

TGI

Agent frameworks

Open-weights models

Job description

Pronoia Energy in Torrance, CA seeks an AI Engineer to build an agent orchestration framework and a verification harness. You will stand up a self‑hosted open‑weights model on local hardware, and design grounding mechanisms that ensure all claims come from sources or deterministic computation.

You will lead an end‑to‑end loop, routing retrieval and tools, while wearing multiple hats as a founding generalist. Onsite role with strong focus on robustness and rapid iteration.