Lead Edge AI & Small Language Model (SLM) Optimization Engineer

Opportunity Overview

Location: 100% Remote (United States)
Employment Type: Full-Time Direct-Hire via Accel DNA
Compensation Range: $185,000 – $220,000 Base + Performance Bonus
Hiring Agency: Accel DNA – Premier Frontier Data & AI Talent Partner

Drive high-efficiency deployment of sub-8B parameter language and vision models on resource-constrained edge hardware, laptops, and localized compute appliances.

Key Responsibilities:

• Compress, distill, and quantize frontier foundation models into lightweight 1B–7B SLMs using AWQ, GPTQ, and EXL2 formats.
• Implement speculative decoding, KV-cache compression, and flash-attention kernels tailored to edge GPUs and Apple Silicon (MLX).
• Deploy offline, zero-latency inference engines using llama.cpp, ONNX Runtime, and TensorRT-LLM.
• Benchmark accuracy tradeoffs against full-scale models across standardized domain-specific evaluation suites.

What You Bring:

• 5+ years in deep learning deployment and systems optimization with strong C++ and Python programming fundamentals.
• Deep expertise in model quantization, knowledge distillation, and hardware-accelerated inference runtimes.
• Experience optimizing LLMs for edge platforms (NVIDIA Jetson, Qualcomm Snapdragon, Apple M-series chips).
• BS/MS in Computer Engineering, Electrical Engineering, or Computer Science.

How to Apply:

Interested in exploring this opportunity? Submit your profile or portfolio directly to contact@accel-dna.com or apply through https://accel-dna.com/contact-us/.