Senior LLMOps & Production Inference Engineer

Opportunity Overview

Location: 100% Remote (United States)
Employment Type: Full-Time Direct-Hire via Accel DNA
Compensation Range: $175,000 – $215,000 Base + Discretionary Bonus + Equity
Hiring Agency: Accel DNA – Premier Frontier Data & AI Talent Partner

An enterprise fintech leader serving millions of daily active users is seeking a seasoned Senior LLMOps & Production Inference Engineer to lead GPU cluster optimization, sub-100ms inference caching, and model lifecycle automation for proprietary financial models.

Key Responsibilities:

• Manage, scale, and optimize low-latency LLM inference engines (vLLM, TensorRT-LLM, TGI, and Triton Inference Server) on cloud GPU infrastructure (NVIDIA H100/A100 clusters).
• Deploy model quantization (AWQ, GPTQ, FP8) and speculative decoding pipelines to maximize throughput and reduce GPU token costs by 40%+.
• Build automated continuous-integration and evaluation (CI/CD) pipelines for open-weight models (Llama 3, Mistral, DeepSeek) with regression tracking.
• Implement real-time model telemetry, drift detection, and automated failover routing across multiple AI cloud providers.

What You Bring:

• 5+ years of software/ML engineering experience with at least 2 years focused on production LLMOps and distributed model inference.
• Expertise with CUDA, PyTorch, vLLM, Docker, Helm, and Kubernetes GPU operator orchestration.
• Strong proficiency in infrastructure-as-code (Terraform) and continuous delivery tooling.
• BS/MS in Computer Science, Computer Engineering, or related technical discipline.

How to Apply:

Ready to build low-latency generative infrastructure at scale? Send your profile to contact@accel-dna.com or apply through Accel DNA Talent Solutions.