Offer summary

Qualifications:

Experience with modern parallelisation frameworks for training such as FSDP, Megatron-LM, or DeepSpeed., Deep theoretical knowledge of deep learning or distributed systems., Comfortable working in research-heavy environments with uncertainty and trade-offs., Familiarity with production scale inference frameworks like ONNX Runtime or NVIDIA Triton..

Key responsabilities:

Productionise advanced ML parallelisation and verification frameworks.

Convert novel hybrid parallelisation and verification research into production code.

Collaborate with team members to ensure effective implementation of machine learning solutions.

Engage in continuous learning and adaptation to new technologies and methodologies.

Job description

Machine intelligence will soon take over humanity’s role in knowledge-keeping and creation. What started in the mid-1990s as the gradual off-loading of knowledge and decision making to search engines will be rapidly replaced by vast neural networks - with all knowledge compressed into their artificial neurons. Unlike organic life, machine intelligence, built within silicon, needs protocols to coordinate and grow. And, like nature, these protocols should be open, permissionless, and neutral. Starting with compute hardware, the Gensyn protocol networks together the core resources required for machine intelligence to flourish alongside human intelligence.

The Role

Bring our distributed ML training research into production

Responsibilities

Productionise advanced ML parallelisation and verification frameworks
Convert novel hybrid parallelisation and verification research into production code

Competencies

Must have

Comfortable working in environments with a heavy research component - and the resulting uncertainty and trade-offs it creates
Demonstrable production experience working with one of the following:
- Modern parallelisation frameworks for training (e.g. FSDP, Megatron-LM, DeepSpeed)
- Frameworks for production scale inference (e.g. ONNX Runtime, TensorRT, DeepSpeed-Inference, NVIDIA Triton, and TorchServe)
Deep theoretical knowledge of deep learning or distributed systems

Preferred

Experience working in high-growth start/scale-up environments
Deep understanding of, and experience with, common networking protocols (IP, TCP, UDP, HTTP) and communication backends (NCCL, GLOO, MPI)

Nice to have

Experience with compiler design
Strong systems programming experience (especially Rust)
Meaningful exposure to decentralised communication, distributed consensus, blockchains

Compensation / Benefits

Competitive salary + share of equity and token pool
Fully remote work - we hire between the West Coast (PT) and Central Europe (CET) time zones
Relocation Assistance - available for those that would like to relocate after being hired (anywhere from PST through CET time zones)
3-4x all expenses paid company retreats around the world, per year
Whatever equipment you need
Paid sick leave
Private health, vision, and dental insurance - including spouse/dependents [🇺🇸 only]

Our Principles

Autonomy & Independence

Don’t ask for permission - we have a constraint culture, not a permission culture.
Claim ownership of any work stream and set its goals/deadlines, rather than waiting to be assigned work or relying on job specs.
Push & pull context on your work rather than waiting for information from others and assuming people know what you’re doing.
Communicate to be understood rather than pushing out information and expecting others to work to understand it.
Stay a small team - misalignment and politics scale super-linearly with team size. Small protocol teams rival much larger traditional teams.

Rejection of mediocrity & high performance

Give direct feedback to everyone immediately - rather than avoiding unpopularity, expecting things to improve naturally, or trading short-term pain for extreme long-term pain.
Embrace an extreme learning rate - rather than assuming limits to your ability / knowledge.
Don’t quit - push to the final outcome, despite any barriers.
Be anti-fragile - balance short-term risk for long-term outcomes.
Reject waste - guard the company’s time, rather than wasting it in meetings without clear purpose/focus, or bikeshedding.
Build thinly - build and design thinly.

Required profile