# RESEARCHER, EFFICIENT INFERENCE at Makermaker Ai

> Onsite · United States · Unspecified · Other · open. Source: https://alderhq.app/jobs/ashby%3Amakermaker.ai%3Ac3677467-8f60-48bc-9997-e3720062e20d (read 2026-11-22).

## Facts (observed)

- Company: [Makermaker Ai](https://alderhq.app/companies/makermaker-ai)
- Location text: San Francisco
- Where it can be done from (inferred): Onsite · United States (evidence: "Location: San Francisco")
- Posted: 2026-09-25 (58 days ago)
- First seen by alder: 2026-11-07 · last verified: 2026-11-17
- Reposted: 0 times · edited: 0 times
- Apply on the employer's site: https://jobs.ashbyhq.com/makermaker.ai/c3677467-8f60-48bc-9997-e3720062e20d
- Skills listed (inferred): PyTorch

## Pay and sponsorship

- Posted pay: not posted
- Market band for similar posted roles (SF Bay Area, n 3586): p25 $90k, median $150k, p75 $200k

## Description (the employer's text)

### ABOUT THE COMPANY

We're building autonomous research agents for recursive self-improvement (multi-agent systems that propose, run, and analyze machine learning experiments). We're a small, well-funded team that works onsite in San Francisco.

### ABOUT THE ROLE

You'll be researching making models efficient: quantization, speculative decoding, sparse and structured attention, distillation, mixture-of-experts inference, and the training-time techniques that make those methods possible. The work spans algorithm design, careful evaluation, and pushing methods to where they actually run.

This is a senior research role with a clear engineering edge. You'll spend time at the intersection of model architecture and inference performance, designing methods that move accuracy/latency/cost trade-offs in our favor (then partnering with engineers to make those wins real in production).

### WHAT YOU'LL DO

Research and develop quantization methods: post-training quantization, quantization-aware training, mixed-precision regimes, low-bit-width arithmetic

Design and evaluate speculative decoding approaches: draft models, tree attention, parallel speculation, lookahead decoding

Investigate training-time efficiency methods that compose well with inference: distillation, sparse attention, mixture-of-experts, low-rank adaptation, pruning

Run controlled experiments at production scale; characterize what works on real workloads, not just toy benchmarks

Co-design methods with the inference engineering team: push results to where they actually run, not stop at the paper

Read deeply across the efficient ML / efficient inference literature; translate the most useful ideas into our stack

Publish when the work warrants it; share findings internally

Partner with model and training researchers so efficiency choices align with model architecture and post-training decisions

### WHAT WE'RE LOOKING FOR

Strong track record of ML research on efficiency methods: quantization, speculative decoding, distillation, MoE, sparse attention, or adjacent

5+ years of hands-on research experience

Deep familiarity with both training and inference performance characteristics

Fluent in PyTorch, Jax or equivalent; comfortable working at the kernel and serving-framework level when methods require it

Track record of moving efficiency research from prototype to production

Strong statistical expertise: you'd notice a flawed comparison before someone else points it out

Strong written communication

Published research at NeurIPS, ICML, ICLR, MLSys, or comparable venues

### NICE TO HAVE

PhD in ML, systems, or related field

Open-source contributions to quantization, speculative-decoding, or efficient-inference libraries

Experience with hardware-aware optimization and accelerator-specific tooling

Background in numerical methods, low-precision arithmetic, or

approximate computation

### THIS ROLE IS PROBABLY NOT FOR YOU IF

You want to focus on pretraining large models from scratch (that's a different role)

You prefer abstract algorithmic research without hands-on implementation

You want a fixed benchmark with stable targets (our targets shift with what our models actually need to do)

---
Data: alder (https://alderhq.app). Cite https://alderhq.app/jobs/ashby%3Amakermaker.ai%3Ac3677467-8f60-48bc-9997-e3720062e20d and the date you read it. Observed facts come from the employer's own listing; location reach, level, family and skills are inferences.
