2 days ago
Palo Alto, CA, USAMid Level
Responsibilities
- Join customer calls with sales, solutions, and leadership and diagnose technical issues through resolution.
- Build and debug integrations with telephony stacks, contact center platforms, mobile and desktop clients, APIs, and SDKs.
- Deploy Sanas models in customer AWS, GCP, Azure, Kubernetes, air-gapped, and private data center environments.
- Size and tune real-time inference workloads across GPU and CPU footprints, latency, concurrency, throughput, and cost.
- Profile and fix production issues involving audio quality, latency, model behavior, networking, and scaling.
- Turn customer-specific fixes into reusable platform features, tooling, and deployment templates.
- Share structured findings with ML research, inference, and platform teams.
- Create runbooks, reference architectures, and integration guides.
Requirements
- At least 2 years of experience shipping production systems.
- Strong Python skills and deep fluency in at least one of Go, C++, or Rust.
- Solid understanding of ML training, evaluation, serving, and real-world model failures.
- Hands-on production model inference experience with serving frameworks such as Triton, TensorRT, ONNX Runtime, or vLLM, plus batching, quantization, and GPU utilization.
- Strong AWS, Docker, Kubernetes, Terraform or equivalent infrastructure-as-code, networking, and security skills.
- Experience deploying software in restricted networks, customer-controlled environments, on-premises hardware, or environments with limited access.
- Excellent debugging ability across distributed, latency-sensitive systems and strong communication with customers and executives.
- Preferred experience includes speech and audio systems, ASR, TTS, machine translation, real-time audio pipelines, codecs, forward-deployed or solutions engineering, telecom or contact center integrations, sovereign or regulated deployments, GPU cluster operations, NVIDIA tooling, CPU-optimized inference, and startup environments.
Categories
Forward Deployed
About Sanas.ai
Sanas builds real-time speech AI that translates accents and enhances clarity on live conversations, helping multilingual agents be more easily understood. It sells the technology as SaaS via APIs, call-center integrations, and an agent desktop app to contact centers, BPOs, and enterprise support and sales teams. The company is privately held and headquartered in Palo Alto, California.
