Research Engineer, Reinforcement Learning

๐Ÿ•’ August 19

๐Ÿ‡บ๐Ÿ‡ธ United States โ€“ Remote

๐Ÿ’ต $135k - $300k / year

โฐ Full Time

๐ŸŸก Mid-level

๐ŸŸ  Senior

๐Ÿ“š Research Engineer

Where this job comes from

Posted on LiveKit's careers page โ†—LiveKit's careers page, not through a job board

First seen by Remote Rocketship August 19

Still open on LiveKit's site. Checked 4 hours ago.

Apply Now
Logo of LiveKit

LiveKit

11 - 50 employees

Founded 2020

๐Ÿ”Œ API

๐Ÿค– Artificial Intelligence

๐Ÿ“ก Telecommunications

๐Ÿ’ฐ Venture Round on 2022-09

API โ€ข Artificial Intelligence โ€ข Telecommunications

LiveKit is a platform designed to facilitate real-time AI and multimedia communications. It enables the instantaneous transmission of audio and video between language models (LLMs) and users, creating real-time multimodal experiences. LiveKit provides tools for developing voice AI, robotics, and livestreaming applications, with ultra-low latency and high resilience. It supports integration with telephony networks, simulating human conversation with advanced features like interruption handling and turn-taking cue detection. The platform is geared towards developers, offering SDK support across all major platforms, allowing applications to be deployed and scaled efficiently. LiveKit is open-source under Apache 2. 0 and offers robust security measures, including end-to-end encryption and compliance with GDPR, SOC2 Type 2, CCPA, and HIPAA.

๐Ÿ“‹ Description

โ€ข Build the environments and verifiers models train against โ€ข Own the synthetic data pipeline from generation through quality gates โ€ข Run end-to-end training experiments and explain model changes โ€ข Build evaluations that releases must pass โ€ข Choose and adapt open-weight base models for LiveKitโ€™s tasks โ€ข Ensure trained behavior works for voice and text agents โ€ข Ship models into production and continuously improve them using real usage โ€ข Build post-training capabilities for agents operating across voice, SMS, and chat channels, including long-horizon context and reliable tool use

๐ŸŽฏ Requirements

โ€ข Strong Python engineering skills โ€ข Experience carrying a model from raw data through production โ€ข Ability to treat data as the product, including coverage, diversity, and leakage โ€ข Ability to design against models exploiting weak rewards โ€ข Comfortable working with GPUs and aware of their limitations โ€ข Ability to determine when to train and when not to train โ€ข Comfortable working collaboratively in a remote environment โ€ข Experience with post-training, fine-tuning, reward design, or reinforcement learning such as GRPO โ€ข Experience with RL and fine-tuning frameworks such as TRL, verl, OpenRLHF, or a self-written training loop โ€ข Experience with fast rollouts using vLLM or SGLang โ€ข Experience with multi-GPU training using FSDP โ€ข Experience training tool-using or multi-turn agents โ€ข Experience with execution sandboxes, verifiers, evaluation harnesses, or tooling โ€ข Experience with open-weight model families such as Qwen or Llama โ€ข Experience with LoRA or similar techniques โ€ข Legal authorization to work in the US or country of residence โ€ข Must indicate whether future sponsorship support is required

๐Ÿ–๏ธ Benefits

โ€ข Equity package โ€ข Health benefits โ€ข Dental benefits โ€ข Vision benefits โ€ข Flexible vacation policy โ€ข Opportunity to shape the brand of a fast-growing developer platform โ€ข Collaboration with a small, senior team that values craft and creativity

Apply Now

๐Ÿ“Š Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Similar Jobs

๐Ÿ•’ August 7

Built

201 - 500

๐Ÿ—๏ธ Construction

๐Ÿ’ผ Consulting

๐Ÿ“ฆ Logistics

Staff Innovation Engineer building AI-powered marketplace services for Built, an AI platform for construction and real estate finance. Developing microservices, customer-tested products, and LLM workflows.

๐Ÿ•’ August 7

Sony Interactive Entertainment

10,000+ employees

๐ŸŽฎ Gaming

๐Ÿ”ง Hardware

๐Ÿ“ก Telecommunications

Senior Security Research Engineer advancing threat exposure management for PlayStation. Leading vulnerability research, validation, prioritization, and remediation across Sonyโ€™s technology environments.

๐Ÿ•’ July 28

Surge AI

51 - 200

๐Ÿค– Artificial Intelligence

๐Ÿ”Œ API

โ˜๏ธ SaaS

Research Engineer at Surge working at the intersection of software engineering and AI training data. Owning coding data projects to teach frontier models how to code.

๐Ÿ•’ July 28

Sequen

11 - 50

โ˜๏ธ SaaS

๐Ÿค– Artificial Intelligence

๐Ÿค B2B

Staff+ Forward Deployed Research Engineer at Sequen developing production-grade systems for AI-driven ranking and recommendations. Working at the intersection of AI research and customized deployment inside enterprise environments.

๐Ÿ•’ July 28

Runway

51 - 200

๐Ÿค– Artificial Intelligence

โ˜๏ธ SaaS

๐Ÿ“ฑ Media

Research Engineer working on AI world modeling and multimodal foundational models at innovative tech company. Collaborating across research efforts and bringing models to production.

Developed byย Lior Neu-ner. I'd love to hear your feedback โ€” Get in touch via DM or support@remoterocketship.com
Follow Remote Rocketship on LinkedInFollow Remote Rocketship on InstagramFollow Remote Rocketship on FacebookFollow Remote Rocketship on TikTok