FewerJobs.
All jobs

Senior Applied Scientist, LLM Code Agents, Kiro Science

Amazon - Santa Clara, California, USA

Posted Oct 28, 2025

Benefits

Parental leave
Not verified
Non-birth-parent leave
Not verified
Family-building benefits
  • Fertility benefits: Offered From the posting source checked Jun 20, 2026
  • Adoption assistance: Offered From the posting source checked Jun 20, 2026
  • Surrogacy assistance: Not verified
Mental health support
Offered From the posting source checked Jun 20, 2026
Relocation assistance
Not verified
Childcare support
Offered From the posting source checked Jun 20, 2026
Learning budget
Not verified
Verification
Not verified checked Nov 20, 2026
Salary
$192K-$260K From the posting source checked Jun 20, 2026
401(k) match
Reported from DOL Form 5500 industry filing (not employer-specific)

Was this benefit information wrong? Tell us.

Market context

U.S. role benchmark (BLS OEWS)
$111,944 U.S. median for this role
Projected growth (BLS Employment Projections)
+13.7% - Much faster than average

102% above the BLS role benchmark for data and ml aggregate.

Matched to SOC 15-1252 - Data and ML aggregate by role bucket.

Source:U.S. Bureau of Labor Statistics, OEWS, May 2024andEmployment Projections, 2024-2034.

Role

Role function
Data From the posting source checked Jun 20, 2026
Seniority
Senior From the posting source checked Jun 20, 2026

Schedule

Shift type
Not verified
Weekend work
Not verified

Company

Company stage
Public-company From the posting source checked Jun 20, 2026
Equity
Offered Verified - SEC 10-K source checked Jun 20, 2026

Application

Cover letter
Not verified
Assessment
Not verified
Deadline
Not stated

Where they hire

State eligibility is not yet verified.

About this role

Senior Applied Scientist, LLM Code Agents, Kiro Science Santa Clara, California, USA One of the key bottlenecks in training capable code agents today is the environment the model is trained on. You can't RL your way to a better coding agent if your training rollouts are running against environments that don't actually reflect how software gets built, have flaky rewards, are prone to reward hacking, or rely on unreliable verification methodology. We're building and improving š—žš—¶š—æš—¼ - Amazon's next-gen AI coding agent - and we're building š˜ƒš—²š—æš—¶š—³š—¶š—²š—± (š—²š˜…š—²š—°š˜‚š˜š—¶š—¼š—»-š—Æš—®š˜€š—²š—± š—¼š—æ š—»š—²š˜‚š—æš—¼š˜€š˜†š—ŗš—Æš—¼š—¹š—¶š—°) š—„š—Ÿ š—²š—»š˜ƒš—¶š—æš—¼š—»š—ŗš—²š—»š˜š˜€ š—®š˜ š˜€š—°š—®š—¹š—². We're looking for someone excited about the problem. The strongest candidates have depth in at least one of: š—£š—æš—¼š—“š—æš—®š—ŗš—ŗš—¶š—»š—“ š—Ÿš—®š—»š—“š˜‚š—®š—“š—²š˜€ / š—¦š—˜ - type systems, compilers, build systems, dependency analysis, program analysis š—”š—½š—½š—¹š—¶š—²š—± š—Ÿš—Ÿš— š˜€ š—®š—»š—± Tš—æš—®š—¶š—»š—¶š—»š—“ - post-training, RLHF / RLVR / RLAIF, distillation, evaluation harnesses, agent scaffolds š—„š—Ÿ š—šš˜†š—ŗ š—±š—²š˜ƒš—²š—¹š—¼š—½š—ŗš—²š—»š˜ - Gymnasium, custom verifiers, reward design, sandboxing š—¦š—¼š—³š˜š˜„š—®š—æš—² š—˜š—»š—“š—¶š—»š—²š—²š—æš—¶š—»š—“ š—®š˜ š˜€š—°š—®š—¹š—² - containerization, deterministic execution, CI/CD systems, hermetic builds Key job responsibilities š—Ŗš—µš—®š˜ š˜†š—¼š˜‚'š—¹š—¹ š˜„š—¼š—æš—ø š—¼š—»: • Designing verified RL environments built from real codebases and post training with these environments • Reward functions that survive Goodhart's law on F2P / P2P / mutation tests • Scaling environment generation pipelines that stay fresh against contamination • Publishing at NeurIPS / ICML / ICLR / ICSE / OOPSLA / ACL About the team The AWS Developer Agents and Experiences (DAE) team is reimagining the builder experience through generative AI and foundation models. We're leveraging the latest

Read the full description at www.amazon.jobs. FewerJobs shows a preview and links to the original posting.

Apply at amazon.jobs

Apply link verified; last checked Nov 20, 2026.

What verified means

Verified means a displayed claim has field-level provenance to a source FewerJobs pulled: a government or employer source, or the original job posting. Posting-sourced facts are employer-stated and are labeled separately from government records.

Related jobs