Neuronify

Inference

Running a trained model to produce outputs. For deployed AI products it is where most of the compute bill, and most of the latency, comes from.

Hiring data as of November 4, 2026 · refreshed daily

companies naming it
14 of 47companies naming it
open roles naming it
44open roles naming it
of those based in NYC
24of those based in NYC
median posted base (n=16)
$238kmedian posted base (n=16)

What Inference means

Inference is the act of using a model, as opposed to training it. Every API call to a language model is inference. For a product in production it dominates cost, because training happens once and inference happens on every request.

Inference engineering is its own specialty: batching requests to keep GPUs busy, caching repeated context, quantizing weights, choosing serving frameworks such as vLLM or TensorRT, and trading latency against throughput. The economics are moving fast enough that purpose-built inference hardware is now a category.

Inference in New York job posts

14 of the 47 New York AI companies we track name Inference in at least one open role today, across 44 postings. 24 of those are based in New York; the rest are remote or in the companies’ other offices.

This is engineering vocabulary: 68% of the postings that name it are Engineering roles.

How to read it

Counted only where the posting also names serving, latency, GPUs, or similar, to exclude the statistical sense of the word. A posting centered on inference is a systems role, strong on performance engineering and GPU behavior.

Go deeper: what running models yourself or through a hosted API asks of your team, in the Neuronify AI Field Guide.

What these roles pay

$215k25th percentile
$238kMedian
$275k75th percentile

Midpoints of 16 distinct salary ranges posted on New York roles that name Inference. Base salary only; on-target earnings are excluded, and a range repeated across one company’s postings counts once. For comparison, the median across all New York engineering postings is $216k. A term’s pay reflects the roles that name it as much as the skill itself — see the role mix below before reading a premium into it. Full bands by function and seniority are in the NYC salary calculator.

Companies naming Inference, daily

Count of companies with at least one open role naming the term. We read between 46 and 47 companies a day over this period, so a move of one or two is noise.

0102014Sep 20Nov 4Sep 20: 14 companiesSep 21: 14 companiesSep 22: 13 companiesSep 23: 13 companiesSep 24: 12 companiesSep 25: 11 companiesSep 26: 11 companiesSep 27: 11 companiesSep 28: 11 companiesSep 29: 11 companiesSep 30: 11 companiesOct 1: 11 companiesOct 2: 11 companiesOct 3: 11 companiesOct 4: 11 companiesOct 5: 11 companiesOct 6: 12 companiesOct 7: 12 companiesOct 8: 12 companiesOct 9: 13 companiesOct 10: 13 companiesOct 11: 13 companiesOct 12: 13 companiesOct 13: 13 companiesOct 14: 13 companiesOct 15: 13 companiesOct 16: 13 companiesOct 17: 14 companiesOct 18: 14 companiesOct 19: 14 companiesOct 20: 14 companiesOct 21: 14 companiesOct 22: 14 companiesOct 23: 14 companiesOct 24: 14 companiesOct 25: 14 companiesOct 26: 14 companiesOct 27: 14 companiesOct 28: 14 companiesOct 29: 14 companiesOct 30: 14 companiesOct 31: 14 companiesNov 1: 14 companiesNov 2: 13 companiesNov 3: 13 companiesNov 4: 14 companies
View as table
Datecompanies
2026-09-2014
2026-09-2114
2026-09-2213
2026-09-2313
2026-09-2412
2026-09-2511
2026-09-2611
2026-09-2711
2026-09-2811
2026-09-2911
2026-09-3011
2026-10-0111
2026-10-0211
2026-10-0311
2026-10-0411
2026-10-0511
2026-10-0612
2026-10-0712
2026-10-0812
2026-10-0913
2026-10-1013
2026-10-1113
2026-10-1213
2026-10-1313
2026-10-1413
2026-10-1513
2026-10-1613
2026-10-1714
2026-10-1814
2026-10-1914
2026-10-2014
2026-10-2114
2026-10-2214
2026-10-2314
2026-10-2414
2026-10-2514
2026-10-2614
2026-10-2714
2026-10-2814
2026-10-2914
2026-10-3014
2026-10-3114
2026-11-0114
2026-11-0213
2026-11-0313
2026-11-0414

Who names it

Open roles naming Inference, by company.

Also: Mirage (fka Captions), Tabs.

Which roles

The same postings, by function and by seniority.

  • Engineering30
  • Research9
  • Other2
  • Product2
  • GTM1
  • Mid17
  • Senior11
  • Staff/Principal9
  • Entry4
  • Manager2
  • Director1

Named alongside Inference

Terms that appear in the same postings far more often than chance would put them there. The number is how many of the 14 companies pair the two.

Open roles naming Inference

A sample from today’s data, New York roles first and one per company before any repeats. Links go to the employer’s own posting. For the full market, see AI jobs in NYC.

On the AI in NYC Show

How this is counted

Every day we read the open roles on the public job boards of the New York AI companies in our coverage — the NYC AI 100 and the AI in NYC Show roster. This term is matched against each role’s description after removing the text a company repeats across its postings, so an “About us” paragraph cannot tag every role the company has open. A vendor’s own postings never count toward its own name.

The figure means named in a job posting. It does not mean used in production, and a “nice to have” counts the same as a requirement. Companies are the headline number because posting counts are dominated by whichever few employers are hiring hardest this month.

Full method, including the pay rules, is on the glossary index; the underlying series is the NYC AI Hiring Index.

Inference — common questions

What does Inference mean in an AI job posting?

Running a trained model to produce outputs. For deployed AI products it is where most of the compute bill, and most of the latency, comes from. Counted only where the posting also names serving, latency, GPUs, or similar, to exclude the statistical sense of the word. A posting centered on inference is a systems role, strong on performance engineering and GPU behavior.

How many New York AI companies are hiring for Inference?

As of November 4, 2026, 14 of the 47 New York AI companies we track name Inference in the description of at least one open role, across 44 postings (24 based in New York). The count refreshes daily from the companies’ own job boards.

What do roles that ask for Inference pay in New York?

Across 16 distinct posted salary ranges on New York roles naming Inference, the median midpoint is $238k base, with the middle half between $215k and $275k. The same figure for all New York engineering postings is $216k. These are employer-posted ranges required by New York’s pay transparency law, base salary only.

Which skills are asked for alongside Inference?

In the same postings, the terms most distinctively paired with Inference are Quantization and distillation, Triton, CUDA, vLLM, GPUs. We rank pairings by how much more often they appear together than apart, so near-universal terms such as Python do not crowd out the informative ones.

Need someone who has actually shipped this?

A keyword in a posting is easy to match and hard to verify. We match companies with AI engineers and consultancies vetted on production work, and tell you when the project needs a different skill than the one you named.

Start a project briefJoin the expert network