Latest AI JobsBrowse Jobs
BrightAI Corporation logo

Senior AI Engineer (Edge Dialog Systems)

BrightAI CorporationPalo Alto, CAEngineering
Apply on company site
Salary
Not listed
Job type
Full-time
Posted
25 Aug 2026
Status
Open · checked 7d ago

About this role

BrightAI Corporation is currently seeking a Senior AI Engineer specializing in Edge Dialog Systems to join the team in Palo Alto, CA. This crucial role centers on taking complete ownership of the on-device conversational AI that runs the company's industrial safety wearable technology.

Role Overview

BrightAI Corporation is seeking a dedicated professional to shape the conversational intelligence powering safety-critical wearables for field technicians. The selected candidate will build and refine local-first dialog systems where deterministic methods handle most conversational turns, utilizing language models strictly as a final resort. This position suits an engineer with deep expertise in edge machine learning, natural language understanding, and robust safety guardrails.

Key Responsibilities

Own the entire on-device dialog pipeline, covering intent routing, hybrid intent classification, text normalization for speech input, and the guided-procedure engine.
Maintain and extend the deterministic safety layer around the language model, including confirmation gating, criticality tagging, and negation handling.
Execute small language model inference directly on devices while strictly respecting memory, computational complexity, and thermal latency budgets.
Preserve and expand the zero-shot configuration model so that new customer procedures are authored as data rather than deployed code.
Coordinate the device deployment pipeline with the edge team, maintaining API contracts with the speech-to-text stack.
Define and execute on-device benchmarks to measure latency, accuracy, and false-accept or false-reject rates.
Build and maintain golden datasets and non-regression suites to serve as release gates for growing command catalogs.
Lead the migration from zero-shot configurations to fine-tuned on-device models to reduce latency without adding customer-specific retraining burdens.
Collaborate across product, firmware, and cloud engineering teams to bring new languages, device commands, and workflows online.

Requirements

Educational background in AI, Machine Learning, Electrical Engineering, Computer Engineering, or a related field with a focus on NLP, speech, or deep learning, or equivalent industry experience.
5+ years of professional experience in machine learning or artificial intelligence with a core focus on NLP, LLMs, or conversational AI.
Strong applied experience with LLMs, structured outputs, tool and function calling, evaluation, and retrieval-augmented generation.
Solid command of embeddings, semantic similarity, threshold tuning, and out-of-domain detection.
Strong Python programming abilities with clean, tested, and reviewable code practices using pytest, Git, and CI discipline.
Solid background in edge conversational systems, multi-turn dialog state management, and efficient local-first intent pipelines.
Experience placing deterministic guardrails, safety floors, state-machines, and workflow engines around probabilistic models.
Practical experience running models on constrained hardware such as NPUs, mobile devices, or embedded targets using ONNX runtime and model quantization.
Working knowledge of embedded development workflows including Linux, Docker, adb, and systemd services.

Nice to Have

Experience with small language model fine-tuning techniques including LoRA, QLoRA, instruction tuning, and model distillation.
Latency and footprint optimization skills such as INT8 and INT4 quantization, ONNX graph optimization, and hardware-aware selection.
Familiarity with building data flywheels from on-device session logs to generate training data.
Background in speech recognition, LLM-as-a-judge evaluation, multilingual NLU, or industrial and safety-critical products.
GO programming language familiarity, exposure to MCP or agentic tooling, and prior startup experience.

Skills and Tools

Python
Docker
LLM
NLP
RAG
ONNX and onnxruntime
Git and pytest
Linux and adb

About the Company

BrightAI Corporation is a high-growth Physical AI company that transforms how businesses interact with the physical world through intelligent automation. The proprietary platform processes visual, spatial, and temporal data from billions of real-world events gathered across edge devices, mobile sensors, and cloud infrastructure to drive intelligent decision-making at scale.

How to Apply

Interested candidates should visit the official BrightAI careers page to submit an application for this position.

Skills and tech stack

PythonDockerLLMNLPRAG

Questions candidates ask

Where is this job located?

This position is based in Palo Alto, CA, offered as a full-time on-site or hybrid role.

How many years of experience are required?

Candidates must have 5+ years of experience in ML or AI with a strong focus on NLP, LLMs, or conversational AI.

What is the primary focus of the Senior AI Engineer role?

The engineer will own and evolve the on-device conversational AI powering industrial safety wearables, focusing heavily on edge dialog systems engineering and safety guardrails.

Are language models the primary decision-makers in this architecture?

No, most conversational turns are resolved by deterministic and embedding-based methods, with language models used as a last resort.

What core technical skills are needed?

Required skills include Python, Docker, LLM, NLP, RAG, ONNX runtime, and experience with embedded or constrained hardware environments.

Ready to apply?

The application is on the official BrightAI Corporation careers page.

Apply on company site