Edge AI Platform Architect - Principal Engineer

Seekr; Menlo Park (CA); Hybrid; USD 190,000 - 320,000; Full time

Benefits offered by this job

Meaningful Mission & Impact

Equity Ownership - RSUs

Unlimited PTO + 14 holidays

Hybrid Work Environment: Reston, VA &/

401(k) with Company Match

Comprehensive Health & Wellness

Parental Leave

Job summary

Seekr is seeking a Staff or Principal AI Engineer to help build SeekrFlow Edge Builder, a platform that packages, configures, deploys, and operates trustworthy AI across edge, on-prem, cloud, disconnected, and air-gapped environments. You will collaborate across AI, software, infrastructure, and security layers to translate deployment requirements into reliable product capabilities.

Your work will shape architecture, developer experience, and operational foundations to make AI deployments

Qualifications

• Experience building production AI/ML platforms, MLOps systems, developer tools, or deployment infrastructure.
• Strong Python, Go, or similar software-development skills.
• Experience with Docker, Kubernetes, Linux, APIs, networking, and infrastructure-as-code.
• Understanding of model serving, inference runtimes, quantization, batching, hardware acceleration, and resource-constrained environments.
• Experience with model formats or runtimes such as ONNX, TensorRT, PyTorch, Triton, vLLM, or similar technologies.
• Experience designing configuration-driven systems, deployment workflows, platform APIs, or orchestration tools.
• Knowledge of secure software development, identity and access management, secrets, encryption, auditability, and supply-chain security.
• Familiarity with edge, on-premises, disconnected, or air-gapped deployments.
• Strong systems-thinking and troubleshooting skills across application, platform, infrastructure, and AI layers.
• Experience building automated testing, observability, diagnostics, and reliability capabilities into platform products.

Responsibilities

• Design and build core capabilities of SeekrFlow Edge Builder for packaging, configuring, deploying, and operating AI solutions at the edge.
• Develop workflows that assemble models, agents, data pipelines, APIs, and supporting services into repeatable edge deployments.
• Build abstractions and tooling for deploying AI workloads across cloud, on-premises, edge, disconnected, and air-gapped environments.
• Implement model and service lifecycle capabilities, including versioning, configuration, validation, upgrades, rollback, and compatibility management.
• Develop infrastructure and orchestration components for containers, Kubernetes, local inference, hardware accelerators, storage, and networking.
• Build optimization features that account for device capabilities, CPU/GPU availability, memory, storage, bandwidth, power, and latency constraints.
• Integrate model-serving runtimes, data connectors, APIs, observability components, security controls, and enterprise systems into the platform.
• Create automated preflight checks, deployment validation, health monitoring, diagnostics, and recovery workflows.
• Build secure-by-default platform capabilities, including identity, access control, secrets management, encryption, audit logging, and software supply-chain protections.
• Develop testing frameworks for functional correctness, deployment compatibility, performance, reliability, and AI model behavior.
• Design APIs, configuration schemas, user workflows, and developer interfaces that make complex edge deployments simple and repeatable.
• Troubleshoot and improve platform behavior across models, runtimes, containers, operating systems, hardware, networking, and customer environments.
• Collaborate with ML, platform, security, product, and customer engineering teams to turn deployment challenges into scalable product capabilities.
• Produce technical documentation, reference architectures, runbooks, and implementation guidance for Edge Builder users and internal teams.

Skills

Python

Go

Docker

Kubernetes

Linux

APIs

Networking

IaC

MLOps

Model serving

Edge deployments

Tools

ONNX

TensorRT

PyTorch

Triton

vLLM

Job description

Seekr is seeking a Staff or Principal AI Engineer to help build SeekrFlow Edge Builder, a platform that packages, configures, deploys, and operates trustworthy AI across edge, on-prem, cloud, disconnected, and air-gapped environments. You will collaborate across AI, software, infrastructure, and security layers to translate deployment requirements into reliable product capabilities.

Your work will shape architecture, developer experience, and operational foundations to make AI deployments