Latest AI JobsBrowse Jobs
F

Forward Deployed Engineer - AI Inference

friendliaiSan FranciscoEngineering
Apply on company site
Salary
Not listed
Job type
Full-time
Work mode
Remote
Experience
Mid · 3+ yrs
Posted
7 Oct 2026
Status
Open · checked 7d ago

About this role

The Forward Deployed Engineer - AI Inference position at FriendliAI is based in San Francisco and suits professionals with a background in DevOps, platform engineering, or reliability engineering for AI applications. This role involves working directly with enterprise clients to operate, scale, and deploy generative and agentic AI workloads using company products like Dedicated Endpoints, Serverless Endpoints, and Friendli Container.

Role Overview

FriendliAI is hiring a Forward Deployed Engineer to assist enterprise customers with inference challenges directly on client projects. The professional will collaborate with engineering teams to solve issues related to scaling, monitoring, and orchestration in a customer-embedded capacity.

Key Responsibilities

Design and implement large-scale deployment architectures for multimodal and LLM inference
Manage and deploy containerized workloads across Kubernetes clusters
Troubleshoot production problems such as performance bottlenecks and apply temporary fixes
Partner with client DevOps teams to integrate infrastructure into CI/CD workflows
Write scripts, Terraform modules, and Helm charts to streamline deployments
Share field insights to influence platform observability, reliability, and scaling strategies
Facilitate technical sessions, webinars, and workshops on infrastructure best practices

Requirements

Minimum of 3 years of professional experience in reliability engineering, DevOps, or cloud infrastructure
Bachelor's or Master's degree in Electrical Engineering, Computer Engineering, Computer Science, or an equivalent field
Technical proficiency in Docker, Kubernetes, Terraform, and Helm
Background in networking, distributed systems, and performance tuning
Practical experience handling GPU-based computing and generative AI model serving workloads
Background in backend systems or AI tooling
Operational experience with workloads on GPC, AWS, or OCI
Debugging and problem-solving capabilities in live environments

Nice to Have

Deploying diffusion models or large language models on clusters or GPUs
Knowledge of inference frameworks such as TensorRT, Triton, vLLM, and DeepSpeed-Inference
Familiarity with monitoring stacks like Grafana, Prometheus, ELK, Loki, and OTEL
Knowledge of networking security and compliance frameworks including SOC 2
Background in supporting hybrid-cloud or on-premises deployments

Skills and Tools

Kubernetes
Docker
Terraform
Helm
AWS, GCP, OCI
Triton, vLLM, TensorRT, DeepSpeed-Inference
Prometheus, Grafana, Loki, ELK, OTEL

Salary and Benefits

Competitive compensation and benefits package
Daily lunch, dinner, unlimited beverages, and snacks
Top-tier hardware support and health check-ups
Flexible working hours

About the Company

FriendliAI provides an inference cloud built to run open-weight models at production scale, offering high output token speed, reduced inference costs, and high uptime for agent workloads.

How to Apply

Interested candidates should apply on the official company careers page.

Skills and tech stack

KubernetesDockerTerraformHelmAWSGCPOCITritonvLLMTensorRTDeepSpeed-InferencePrometheusGrafanaLokiELKOTELLLMLLMsDiffusionGenerative AIDistributed Systems

Questions candidates ask

Where is the Forward Deployed Engineer role located?

The position is based in San Francisco.

How many years of experience are required for this role?

Candidates must have 3 or more years of experience in cloud infrastructure, reliability engineering, or DevOps.

What educational background is needed?

A Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or an equivalent field is required.

What technologies and tools are used in this position?

Required tools include Kubernetes, Docker, Terraform, and Helm, with optional familiarity with inference frameworks like vLLM and Triton, and observability stacks like Prometheus and Grafana.

What perks and benefits are provided?

Benefits include competitive compensation, daily lunch and dinner, unlimited snacks and beverages, health check-ups, top-tier hardware support, and flexible working hours.

Ready to apply?

The application is on the official friendliai careers page.

Apply on company site