Forward Deployed Engineer (Inference)

Location: San Francisco, CA; on-site

Salary: $180,000–$300,000 per year

Company

AI infrastructure company building systems that optimize inference workloads across different types of silicon for high-volume, mission-critical AI applications.

What you will do

• Own customer engagements from technical handoff through evaluation, deployment, production operation, and expansion.
• Profile, benchmark, and trace customer workloads using real models and traffic.
• Design and lead technical evaluations, explaining methodologies, results, constraints, and tradeoffs to engineering teams.
• Implement inference workloads in production across inference engines, model serving, infrastructure, observability, and performance tooling.
• Own production performance and reliability, including on-call support and direct debugging of latency, throughput, reliability, and error-rate regressions.
• Maintain technical relationships with customer engineering teams and turn recurring problems into product improvements.

Requirements

• Strong systems-engineering fundamentals and experience owning technical problems through production deployment.
• Understanding of LLM inference fundamentals, including prefill, decode, latency, throughput, and performance tradeoffs.
• Experience profiling, benchmarking, and tracing complex systems, reading traces, and identifying performance bottlenecks.
• Ability to work across unfamiliar systems, operate under ambiguity and urgency, and turn incomplete requirements into working implementations.
• Strong technical communication skills with highly technical customers and engineering audiences.
• Strong production ownership and debugging instincts.

Nice to have

• Experience with LLM inference engines, model-serving infrastructure, GPU or accelerator optimization, or distributed inference.
• Experience with CUDA, Triton, TensorRT-LLM, vLLM, SGLang, Kubernetes, GPU profiling, or tracing tools.
• Customer-facing engineering, solutions architecture, forward-deployed engineering, or latency-sensitive production experience.

Culture & Benefits

• Highly technical, hands-on environment with significant individual ownership and autonomy.
• Broad problem-solving across the stack rather than narrowly defined coding responsibilities.
• Fast-moving production environment focused on benchmarking, profiling, debugging, implementation, and operations.
• Team values include resourcefulness, technical ability, high standards, collaboration, emotional intelligence, rapid learning, and first-principles thinking.