Forward Deployed Engineer

Sanas•Palo Alto, CA

About The Position

The Forward Deployed Engineer is a customer-facing software engineer who makes Sanas models work in customer environments and operations. The role joins customer calls, diagnoses problems, and delivers solutions, including integration code, deployment configuration, and platform fixes. The work focuses on real-time speech-to-speech Language Translation running on customer infrastructure and increasingly on Sovereign AI deployments. Sanas AI models and solutions may be deployed in a customer’s AWS account or private data center without data leaving the customer’s environment. The engineer works closely with key customers on important deployments, contributing to system architecture and product direction as well as production integrations. The role owns problems end to end, from initial customer discussions through live production traffic.

Requirements

  • At least 2 years of experience shipping production systems.
  • Deep fluency in Python and at least one of Go, C++, or Rust.
  • A solid grasp of ML fundamentals, including how models are trained, evaluated, and served, and why they fail in real-world settings.
  • Hands-on experience with production model inference, including serving frameworks such as Triton, TensorRT, ONNX Runtime, or vLLM, as well as batching, quantization, and GPU utilization.
  • Strong cloud and infrastructure skills, including in-depth AWS knowledge, Docker, Kubernetes, Terraform or equivalent infrastructure as code, and networking and security basics.
  • Comfort deploying into environments outside the engineer’s control, including restricted networks, customer security reviews, limited-access environments, and on-premises hardware.
  • Excellent debugging instincts across distributed, latency-sensitive systems.
  • Clear communication with customers and executives, including explaining technical issues to different audiences.
  • High ownership and willingness to see customer problems through to resolution.

Nice To Haves

  • Speech and audio experience, including ASR, TTS, machine translation, real-time audio pipelines, or codecs.
  • Prior experience in a forward-deployed, solutions engineering, or customer-facing engineering role at an infrastructure or AI company.
  • Telecom or contact center integration experience, including SIP trunks, carrier networks, or CCaaS platforms.
  • Experience with sovereign or regulated deployments, including air-gapped installations, data residency, or healthcare or government compliance.
  • Experience with GPU cluster operations, NVIDIA tooling, or CPU-optimized inference.
  • Startup experience, comfort with ambiguity, and a habit of documenting work.

Responsibilities

  • Join customer calls with sales, solutions, and leadership; diagnose technical issues live and own them through resolution.
  • Build and debug integrations between Sanas and customer systems, including telephony stacks, contact center platforms, mobile and desktop clients, APIs, and SDKs.
  • Deploy Sanas models on customer infrastructure, including AWS, GCP, or Azure accounts, Kubernetes clusters, air-gapped environments, and private data centers.
  • Size and tune inference for real-time workloads, including GPU and CPU footprints, latency budgets, concurrency, throughput, and cost per session.
  • Profile and fix production problems across the stack, including audio quality, latency spikes, model behavior, networking, and scaling.
  • Turn one-off customer fixes into reusable platform features, tooling, and deployment templates.
  • Bring structured findings to ML research, inference, and platform teams, explaining what broke, why, and what should be built.
  • Produce runbooks, reference architectures, and integration guides to make subsequent deployments faster.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service