Senior AI Engineer (Edge Dialog Systems)
Brightai · Palo Alto, CA
About this role
**Senior AI Engineer (Edge Dialog Systems)** BrightAI is a high-growth Physical AI company transforming how businesses interact with the physical world through intelligent automation. Our AI platform processes visual, spatial, and temporal data from billions of real-world events captured across edge devices, mobile sensors, and cloud infrastructure—enabling intelligent decision-making at scale. We’re hiring a **Sr. AI Engineer – Edge Dialog Systems** to own and evolve the **on-device conversational AI** that powers our industrial safety wearable. The assistant guides field technicians through **safety-critical procedures by voice**, running directly on the device under strict **latency, memory, and thermal** constraints, with **deterministic safeguards** that take precedence over model output. This is a **systems role** (not prompt-and-retrieve). Strong LLM/RAG engineering skills are needed, but the work is primarily **dialog systems engineering at the edge**, where most turns are resolved via **deterministic and embedding-based methods**, and the language model is the **last resort**. --- ## Responsibilities - Own the **on-device dialog pipeline end to end**: intent routing, hybrid intent classification (pattern matching + embedding similarity + out-of-domain detection), text normalization for noisy speech, and a multi-step guided-procedure engine. - Maintain and extend the **deterministic safety layer** around the language model (confirmation + echo-back gating, criticality tagging, negation handling) so misheard safety-critical answers can’t pass silently. - Run **SLM inference on-device** within memory/compute/latency budgets; reduce per-turn inference cost via model selection, quantization, and runtime optimization. - Preserve and extend the **zero-shot configuration model** where new device commands and customer procedures are authored as data (not code) to onboard new customers in hours. - Coordinate the **device deployment pipeline** with the edge team. - Maintain the **API contract** with the on-device voice pipeline and its **speech-to-text (STT)** stack. - Define and run **on-device benchmarks** (latency, accuracy, false accept/reject rates) for safety-critical steps; use results to drive engineering decisions. - Build and maintain **golden datasets** and a **non-regression suite** as command/procedure catalogs grow. - Lead migration from **zero-shot to fine-tuned on-device models** to reduce latency without creating a per-customer retraining burden. - Collaborate with product, firmware, and cloud teams to bring new capabilities online (additional languages, device commands, guided workflows). --- ## Educational Background - Trained in **AI, Machine Learning, Electrical/Computer Engineering**, or related field, with specialization in **NLP, speech, or deep learning**—or equivalent production experience. - Applied background in **NLU, dialog systems, or on-device machine learning**. --- ## Required Skills & Expertise ### LLM and retrieval foundation (baseline) - **5+ years** in ML/AI with strong focus on **NLP, LLMs, or conversational AI**. - Applied experience with LLMs: prompting, structured output, tool/function calling, evaluation, and **RAG**—plus the judgment to know when not to use a model. - Strong command of **embeddings and semantic similarity** (cosine similarity, centroid vs. max-similarity strategies, threshold tuning, out-of-domain detection). - Strong **Python** with clean, tested, reviewable code; flue
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.