AI Engineer - Model Performance

Dormont Manufacturing Co; San Francisco (CA); On-site; USD 120,000 - 150,000; Full time

Benefits offered by this job

Competitive compensation and benefits

Supportive environment for innovation and growth

Job summary

Dormont Manufacturing Co is seeking a Model Performance Engineer to enhance the efficiency of our model inference stack and improve our AI team's operational capabilities. You will focus on optimizing system performance for large-scale applications while troubleshooting issues in production environments.

The ideal candidate will possess deep expertise in LLM serving frameworks, strong skills in Python programming, and a solid understanding of GPU performance analysis. Our company offers competitive compensation, a dynamic work environment, and opportunities for professional growth.

Qualifications

• Deep experience with LLM serving frameworks such as vLLM or SGLang.
• Hands-on experience with quantization techniques and tuning.
• Experience in production fine-tuning processes with frameworks like LoRA or QLoRA.
• Strong proficiency in Python programming for developing infrastructure.
• Ability to conduct GPU profiling and performance evaluations.

Responsibilities

• Optimize model inference stack for speed and reliability.
• Benchmark and evaluate GPU families for optimal performance.
• Debug and troubleshoot production inference issues.
• Construct fine-tuning pipelines for AI models.
• Enhance GPU cost modeling and resource allocation strategies.

Skills

Deep experience with LLM serving frameworks

Hands‑on quantization experience

Production fine-tuning experience

Strong Python

Comfort with GPU profiling and performance analysis

Job description

ROLE OVERVIEW

We’re hiring a Model Performance Engineer to own the speed, cost, and reliability of our model inference stack, and to build the fine-tuning infrastructure that makes the rest of the AI team faster.

This is not a research role. You’ll be optimizing real systems serving millions of meetings — choosing between quantization trade-offs, debugging speculative decoding, or figuring out why one GPU family’s tail latency explodes at high concurrency while another stays stable.

You’ll own two things:

HOW YOU’LL HELP US WIN

• Benchmark FP8 quantization across GPU families, find that FP8 KV cache causes catastrophic repetition loops, identify static quantization as 6% faster than dynamic on certain hardware, and ship a production config that gets 1.3x speedup with <1% quality degradation.
• Evaluate serving frameworks (vLLM vs SGLang) with speculative decoding — discover that ngram speculation degrades ASR quality while EAGLE3 draft models don’t, and that torch.compile makes certain GPUs 7% slower.
• Build a fine-tuning pipeline that takes a JSONL dataset and produces an optimized tune ready for serving, so a teammate can train a small classifier in an afternoon instead of a week.
• Optimize GPU spend — know which GPU families are best for batch workloads (stable under high concurrency) vs latency-sensitive paths (40% faster, but tail latency blows up under load), and when a 30% cost premium isn’t worth it.
• Debug production inference issues — trace a quality regression to a serving framework upgrade that changed the default attention backend, or find that audio format handling in the multimodal pipeline silently drops segments.

REQUIREMENTS

Hard Skills:

• Deep experience with LLM serving frameworks (vLLM, SGLang, TensorRT-LLM, or similar) — not just deploying them, but tuning them: attention backends, scheduling strategies, CUDA graph warmup, prefix caching.
• Hands‑on quantization experience — you’ve gone beyond “apply FP8 and hope.” You understand weight vs activation quantization, per-channel vs per-tensor scaling, and when dynamic quantization introduces more overhead than it saves.
• Production fine-tuning experience — LoRA/QLoRA SFT, familiarity with training frameworks (ms‑swift, Axolotl, torchtune, or similar), understanding of data formatting, learning rate schedules, and how to diagnose training failures.
• Strong Python. You’ll write serving infrastructure, benchmarking harnesses, and training pipelines — not notebooks.
• Comfort with GPU profiling and performance analysis. You should be able to look at a benchmark result and know whether the bottleneck is compute, memory bandwidth, or scheduling overhead.

Strong signal:

• Cost modeling for GPU infrastructure — you’ve had to choose between GPU types and justify the tradeoff.
• Experience with multimodal models (audio/vision encoders + LLM decoders).
• Experience with Modal, Ray Serve, or similar serverless GPU platforms.
• Understanding of audio processing (codecs, chunking, sample rates).
• Experience building internal tooling that other engineers use — this role succeeds when the rest of the team ships faster.

Not required:

• ML research background or publications.
• Prompt engineering expertise (we have a team for that).
• Frontend or full-stack experience.
• Masters/PhD (though it’s fine if you have one).

WHAT’S IN IT FOR YOU

• The opportunity to shape the foundational software services of a growing company.
• A role that balances innovation and incremental improvement.
• A dynamic and collaborative engineering team.
• Competitive compensation and benefits.
• A supportive environment that encourages innovation and personal growth.