Anthropic Curated from employer
Performance Engineer, Inference Systems
San Francisco / New York City / Seattle · Hybrid
USD $350,000–$850,000 / yearView role Source checked 2026-10-30
SPECIALIST CAREERS · CANADA & THE US
Inference engineer jobs
Make trained models perform reliably in production. Browse LLM inference, model serving and AI infrastructure roles across Canada and the US.
GPU servingLatency & throughputDistributed systemsPerformance measurement
APPLY DIRECTLY WITH EMPLOYERS
9 current roles
fal Curated from employer
Machine Learning Engineer, Safety
San Francisco · On-site five days a week · Full-time
USD $180,000–$250,000 / yearView role Source checked 2026-10-30
Tubi Curated from employer
Staff Software Engineer, ML Infra & Distributed Systems
Toronto, Ontario · Hybrid
CAD $164,600–$235,100 / yearView role Source checked 2026-10-30
USD $200,000–$250,000 / yearView role Source checked 2026-10-30
General Compute Curated from employer
Inference Engineer
San Francisco / New York City · Hybrid · Full-time
Pay: see employerView role Source checked 2026-10-30
Baseten Curated from employer
Forward Deployed Engineer (Training)
San Francisco / New York · Hybrid · Full-time
USD $200,000–$400,000 / yearView role Source checked 2026-10-30
Modal Curated from employer
Forward Deployed Engineer - ML
New York / San Francisco · On-site · Full-time
USD $180,000–$250,000 / yearView role Source checked 2026-10-30
Modal Curated from employer
Forward Deployed Engineer - Systems
New York / San Francisco · On-site · Full-time
USD $180,000–$240,000 / yearView role Source checked 2026-10-30
Cohere Curated from employer
Forward Deployed Engineer, Inference
United States · On-site · City not specified · Full-time
USD $240,000–$325,000 base / year*View role Source checked 2026-10-30
No matching roles right now.
Try another skill or remove a filter. We’re starting with a small, focused selection.
Each role shows its source-check date and known location restrictions. A listing can close before its review window ends; confirm current availability with the employer. How we review listings.
UNDERSTAND THE WORK
Inference engineering
career guide.
By TaskBull AIJobs · Updated October 30, 2026
Inference engineering focuses on running models
Inference is the work of serving a trained model to produce outputs. Engineers in this area can build serving platforms, improve runtime performance, manage deployment and investigate reliability. The focus differs from training a new model, although the systems and skills can overlap. Read whether a vacancy owns low-level performance, platform operations or integration with customer workloads.
Compare serving runtimes and infrastructure responsibilities
An LLM inference engineer might work with batching, caching, scheduling or GPU memory. Platform roles can also involve model onboarding, observability, rollout controls and capacity planning. Tools such as vLLM, TensorRT-LLM or SGLang appear in parts of this field, but no single runtime defines every job. Compare the employer’s actual stack and expected level of systems expertise.
Show measurements with enough context to be meaningful
For a portfolio experiment, state the model, hardware, request pattern and measurement method. Compare latency, throughput and cost alongside output correctness. Explain warm-up, concurrency and tradeoffs rather than reporting a single unexplained speedup. A reproducible benchmark and a careful account of limitations help an interviewer understand whether the result would transfer to a production workload.
Check location and seniority before applying
Infrastructure vacancies can require substantial distributed-systems or performance experience. Some are office-based even when the wider company hires remotely. Use the role’s stated arrangement and country restrictions. Employer pay bands vary with seniority, location and compensation structure; the examples on this board are individual vacancies, not a salary survey of the inference engineering market.
Sources and reading
Career guidance draws on the examples below and TaskBull’s editorial analysis. Employer sources describe their own roles; they do not endorse this board.
BEFORE YOU APPLY
Your career
questions.
What other titles describe inference engineering?
AI inference platform engineer, inference systems engineer, model serving engineer and ML infrastructure engineer can overlap. Some ML infrastructure jobs focus on training instead, so check the duties.
Is inference engineering the same as prompt engineering?
No. These roles usually emphasize serving infrastructure, systems performance and reliable deployment. Prompt design can affect a workload, but it does not replace the required systems skills.