TuringCoding & software eval
ML Engineer - LLM & Agentic Evaluations
Pay not published
About this role, in Turing's words
We are hiring ML Engineers to join our AI Evaluation team, where you will help design and execute evaluations for Large Language Models (LLMs) and agentic AI workflows. You will work alongside ML engineers, researchers, and domain experts to measure model capabilities, surface failure modes, and improve the way frontier AI systems are trained and benchmarked. This is a hands-on, research-flavored role. You will work on real evaluation problems that directly influence how leading AI models are trained, refined, and shipped
Candidate background
Requirements
- Currently pursuing or recently completed a Bachelor's, Master's, or PhD in Computer Science, Machine Learning, Data Science, Mathematics, or a related quantitative field.
- Strong programming skills in Python, including familiarity with the standard data and ML stack (NumPy, Pandas, Jupyter, etc.).
- Working understanding of how modern LLMs are trained, prompted, and evaluated.
- Experience interacting with LLM APIs (OpenAI, Anthropic, Google, open-source via Hugging Face / vLLM, etc.).
- Strong analytical and writing skills — ability to clearly document tasks, results, and recommendations.
- Comfortable working independently in a fully remote environment with overlapping collaboration hours.
Nice to Have
Show all 6 itemsHide these 6 items in Nice to Have
- Prior experience designing or running LLM evaluations or benchmarks (e.g., MMLU, GPQA, SWE-bench, GAIA, AgentBench, BIG-bench, HumanEval, TerminalBench, WebArena).
- Hands-on experience with AI agent frameworks (LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, etc.) or building tool-using agents from scratch.
- Familiarity with LLM-as-a-judge methodologies, inter-annotator agreement, and statistical analysis of model outputs.
- Experience with prompt engineering, few-shot design, and structured output formats (JSON Schema, function calling).
- Exposure to RLHF / RLAIF, fine-tuning, or post-training data pipelines.
- Background in software engineering, data annotation tooling, or research publications in NLP / ML.
Quoted from selected sections of Turing's posting. The full posting may state other conditions. Read the full posting
A closer look
More context, when you need it.
Full job descriptionThe original posting, in Turing's words
Posted by Turing, reproduced here so you can judge the role before clicking. Original posting ↗
About Turing
Based in San Francisco, California, Turing is the world’s leading research accelerator for frontier AI labs and a trusted partner for global enterprises deploying advanced AI systems. Turing supports customers in two ways: first, by accelerating frontier research with high-quality data, advanced training pipelines, plus top AI researchers who specialize in coding, reasoning, STEM, multilinguality, multimodality, and agents; and second, by applying that expertise to help enterprises transform AI from proof of concept into proprietary intelligence with systems that perform reliably, deliver measurable impact, and drive lasting results on the P&L
Role Overview
We are hiring ML Engineers to join our AI Evaluation team, where you will help design and execute evaluations for Large Language Models (LLMs) and agentic AI workflows. You will work alongside ML engineers, researchers, and domain experts to measure model capabilities, surface failure modes, and improve the way frontier AI systems are trained and benchmarked. This is a hands-on, research-flavored role. You will work on real evaluation problems that directly influence how leading AI models are trained, refined, and shipped
What does day-to-day life look like? Design, build, and run evaluation suites for LLMs across reasoning, coding, math, tool use, and long-context tasks. Develop benchmarks and rubrics for agentic workflows, including multi-step planning, tool/function calling, code execution, and browser/computer-use agents. Curate, clean, and annotate evaluation datasets; write clear task specifications and grading criteria. Run model comparisons (open-source and frontier models), analyze results, and produce structured reports with actionable insights. Implement automated graders (programmatic checks, LLM-as-a-judge) and validate them against human reference judgments. Investigate failure cases, characterize error patterns, and write reproducible findings for the research team. Collaborate with engineers to integrate evaluations into internal harnesses, CI pipelines, and dashboards. Contribute to internal documentation, best practices, and tooling improvements.
Requirements
• Currently pursuing or recently completed a Bachelor's, Master's, or PhD in Computer Science, Machine Learning, Data Science, Mathematics, or a related quantitative field.
• Strong programming skills in Python, including familiarity with the standard data and ML stack (NumPy, Pandas, Jupyter, etc.).
• Working understanding of how modern LLMs are trained, prompted, and evaluated.
• Experience interacting with LLM APIs (OpenAI, Anthropic, Google, open-source via Hugging Face / vLLM, etc.).
• Strong analytical and writing skills — ability to clearly document tasks, results, and recommendations.
• Comfortable working independently in a fully remote environment with overlapping collaboration hours.
Nice to Have
• Prior experience designing or running LLM evaluations or benchmarks (e.g., MMLU, GPQA, SWE-bench, GAIA, AgentBench, BIG-bench, HumanEval, TerminalBench, WebArena).
• Hands-on experience with AI agent frameworks (LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, etc.) or building tool-using agents from scratch.
• Familiarity with LLM-as-a-judge methodologies, inter-annotator agreement, and statistical analysis of model outputs.
• Experience with prompt engineering, few-shot design, and structured output formats (JSON Schema, function calling).
• Exposure to RLHF / RLAIF, fine-tuning, or post-training data pipelines.
• Background in software engineering, data annotation tooling, or research publications in NLP / ML.
Perks of Freelancing With Turing
• Work in a fully remote environment.
• Opportunity to work on cutting-edge AI projects with leading LLM companies.
Offer Details
• Commitments Required: Minimum 20 hours per week with overlap of at least 5 hours/day with PST.
• Engagement Type: Contractor assignment (no medical/paid leave)
• Duration of Contract: 3 months (adjustable based on engagement)
• Location: LATAM
Evaluation Process
• Technical Interview
Working with TuringPay, getting started and work, from Turing's own pages
What the platform publishes in general. These are not extra terms confirmed for this particular role.
- Getting paid
- Paid monthly, around the 5th, straight to your bank account, or inside Deel on projects run through Deel. Its help articles disagree on whether that is the 5th calendar day or business day. help.turing.com/articles/9691407757-project-onboarding, help.turing.com/articles/6582454854-what-if-i-haven-t-rec..., help.turing.com/articles/1226770947-project-offboarding
- Before your first paid task
- A short application, with tests on some roles. Turing's review article says an interview is typically required for all roles. Onboarding covers the terms, ID verification with a driver's license or passport, and tax and payment details. help.turing.com/articles/2020987592-apply-for-jobs-at-turing, help.turing.com/articles/9179629201-how-long-does-the-app..., help.turing.com/articles/9691407757-project-onboarding
- How much work
- Review takes from 48 hours to 6 weeks after you finish applying, and the client makes the final choice. No reply within 6 weeks usually means you were not selected. help.turing.com/articles/9179629201-how-long-does-the-app..., help.turing.com/articles/2020987592-apply-for-jobs-at-turing
- Contract
- Depending on the project, the engagement rests on Turing's Terms of Service and a Service Agreement, on Deel, or on a partner that provides the contract. help.turing.com/articles/6582454854-what-if-i-haven-t-rec...
Read on the pages linked above on 23 Sep 2026. Platforms change these terms, so check the linked page before you rely on one.
How does the pay compare?Across Coding & software eval roles, not this role alone
From our own daily reads of every open listing on the platforms we follow, not from Turing's posting. How we count.
Pay across the field: Coding & software eval
Across 412 roles in this field with a stated hourly rate in US dollars, on 18 platforms, the middle half pays $60 to $120 an hour at the top of the range, and the median is $80.
| Platform | Roles | Top of range, per hour |
|---|---|---|
| Alignerr | 97 | $50 to $200 · median $100 |
| Anyone AI | 79 | $35 to $150 · median $65 |
| micro1 | 42 | $50 to $400 · median $100 |
| AfterQuery | 37 | $45 to $200 · median $100 |
| Meridial (Invisible) | 35 | $22 to $150 · median $50 |
Sources and listing historyWhere this information comes from
This listing's history
- First seen here on 18 Nov 2026, and still on Turing's list when we last read it on 21 Nov 2026.
- Posted by Turing
- First seen by AIPayList
- Last seen live
- Listing ID
- 118678
This role has 2 listings with the same title and pay. I treat them as one role, open in 4 countries.
Keep exploring
More like this
Related field, different requirements. Check each role's own page before you apply.