We're looking for a Lead ML Engineer to own the performance and technical direction of our language models. About two-thirds of your time goes into hands-on inference work: making very large models, up to a trillion parameters and beyond, run faster and cheaper in production on distributed GPU infrastructure. The rest goes into technical leadership of our NLP and CV engineers.

You lead through expertise, not project management. You review experiments, set technical direction and catch wrong turns early, while deadlines and delivery tracking stay with others. This is a hands-on role. We move fast and expect you to go from idea to deployed result in days, not months. As the team grows, there is a clear path to Head of ML.

• Speed up and scale LLM inference in production: SGLang, KV and prefix caching, batching, quantization, speculative decoding
• Run distributed inference for very large models (up to 1T+ parameters) across multi-GPU and multi-node setups
• Benchmark new GPU servers and hardware, bring them into production and adapt our serving code to them
• Lead the NLP and CV teams technically: review experiments, set direction, and step in early when something is heading the wrong way
• Train and fine-tune the language models behind our AI companions, and improve the agent harnesses and chat algorithm that run on them
• Track cutting-edge research and open-source work in inference and post-training, and turn it into the ML roadmap
• Collaborate closely with the validation, content, and dataset preparation teams to design experiments and measure model quality

• Deep hands-on experience optimizing LLM inference in production with SGLang, vLLM, or TensorRT-LLM
• Experience with distributed inference or training of large models: MoE, tensor/expert/pipeline parallelism, multi-node GPU clusters
• Strong understanding of what makes inference fast: KV cache, attention kernels, batching, quantization, GPU profiling
• Experience training and fine-tuning LLMs, including post-training (RLHF, DPO, or similar)
• Proven technical leadership: you've guided engineers through reviews, mentoring and technical decisions while still writing code yourself
• Proficiency with PyTorch, transformers, and related libraries
• Experience at AI-focused startups or companies (Character AI, OpenAI, and similar is a strong plus)
• Backend engineering experience (Python, Go, C#) and knowledge of scalable deployment systems is a significant advantage
• Advanced English or Russian
  

Nice to have:

• CUDA or Triton kernel development
• A computer vision background. We also welcome strong CV leads who have accelerated large generative image or video models
• Experience with multimodal LLMs
• First-author papers or notable open-source work, e.g. contributions to SGLang, vLLM, or post-training libraries
• A degree in CS, math, or physics from a strong program (MSc or PhD)

• We're changing the industry and making relationships with AI feel real
• Opportunity to receive company equity
• Joi Lab gives you access to frontier model research, all open-source and free of corporate gatekeeping
• Small team, high trust, high ownership. You see the direct impact of your work
• Ideas turn into live experiments in days, not quarters
• Fully remote, full-time, work from anywhere
• Offline meetups with the team, fully covered by the company
• We cover 100% of training and conference costs
• Health support: join our group insurance plan, or get up to $1,000 a year toward medical costs or a private plan
• Workspace: we cover your office, home office or co-working setup
• 28 days of annual leave
• 7 wellness days a year for life admin or recovery, no sick notes needed
• Subsidised English classes through our corporate discount
• Peer recognition: send each other gratitude bonuses and swap them for swag, massage vouchers or team trips