Freelancing |RL GYM - AI Researcher | Remote | Immediate Joiner

RL GYM - AI Researcher Role Overview: We are looking for highly driven AI Researchers to join our RL Gym team at Turing. This role is focused on pushing the quality, efficiency, and scalability of AI training and evaluation systems. We are specifically looking for researchers who possess a deep understanding of modern AI systems and can rethink existing workflows, identify inefficiencies, and reinvent processes to make systems smarter, faster, and easier to operate at scale. The ideal candidate should be capable of connecting research thinking with practical execution, while continuously exploring new methods to improve AI training environments, evaluation systems, and operational workflows. What does day-to-day life look like?

• Research and improve AI training, evaluation, and benchmarking workflows.
• Identify bottlenecks in existing systems and redesign processes for higher efficiency and scalability.
• Build innovative approaches for task generation, evaluation, automation, and model quality improvement.
• Analyze AI model behavior, reasoning patterns, hallucinations, and edge cases.
• Design frameworks that simplify complex workflows and reduce operational overhead.
• Drive experimentation and propose new ideas that can significantly improve productivity and quality.
• Collaborate with engineering, program management, and quality teams to operationalize research insights.
• Continuously explore advancements in LLMs, RLHF, AI agents, and emerging research trends.

Requirements:

• Freshers or experienced candidates with a Bachelor’s or master’s degree in computer science, AI, Data Science, or related fields
• Strong understanding of AI/ML concepts, LLMs, NLP, reasoning models, and reinforcement learning workflows.
• Ability to deeply analyze systems and redesign workflows from first principles.
• Strong research mindset with the ability to challenge existing approaches and innovate better solutions.
• Experience with prompt engineering, model evaluation, synthetic data, or AI workflow optimization.
• Strong analytical and problem-solving skills.
• Familiarity with Python and AI tooling/frameworks is preferred.
• Excellent communication and documentation skills.
• Ability to independently drive ambiguous research problems.

Preferred Qualifications:

• Experience working on RLHF, LLM evaluation, AI agents, or model alignment workflows.
• Experience designing scalable AI evaluation or automation systems.
• Exposure to multi-agent systems, reasoning models, or workflow orchestration.
• Prior experience in AI research labs, frontier AI teams, or fast-paced AI startups.

What We’re Looking For:

• Deep curiosity about how AI systems work internally.
• Strong AI research and systems-thinking capability is required. Experience building internal tools, automation systems, APIs, or lightweight full-stack workflows is a plus.
• Ability to reinvent and simplify processes instead of following conventional approaches.
• High ownership and execution capability.
• Research-driven thinking with practical implementation ability.
• Someone who constantly explores how AI can replace, optimize, or accelerate workflows.

Perks of Freelancing with Turing:

• Hands-on experience working on real-world ML/AI problems
• Opportunity to contribute to Frontier Data Labs initiatives and forward-looking AI projects.

Offer Details:

• Commitments Required: 40 hours per week with overlap of 8 hours with PST.
• Engagement Type: Contractor assignment (no medical/paid leave)
• Duration of Contract: 3 months (adjustable based on engagement)
• Location: USA (excluding California, Massachusetts, Washington, New York City), Brazil & Colombia.

Evaluation Process:

• 1 round of technical Interview (60 mins)

Apply tot his job Apply To this Job