All Positions
AI ProductsAtlanta, GAFull-Time
ML Engineer — Inference Optimisation
Make TAL models faster and cheaper to run — closing the gap between research model quality and production serving cost.
About This Role
A model that can't be served cheaply can't reach everyone. The Inference team makes TAL models blazingly fast so we can fulfill our universal access commitment.
Responsibilities
- ▸Profile and optimise LLM inference latency and throughput using vLLM, TensorRT-LLM, and custom CUDA kernels
- ▸Implement quantisation, speculative decoding, and KV cache optimisation techniques
- ▸Build serving infrastructure that scales from zero to millions of requests
- ▸Benchmark inference performance across hardware configurations
- ▸Collaborate with research team to ensure optimised models maintain quality
Requirements
- ▸BS/MS in Computer Science or Electrical Engineering
- ▸3+ years ML engineering with a focus on inference or model serving
- ▸Deep understanding of GPU architecture, CUDA programming, and memory management
- ▸Experience with vLLM, TensorRT, ONNX, or similar inference frameworks
- ▸Proficiency in Python and C++
Nice to Have
- ▸Experience with FlashAttention, PagedAttention, or similar attention optimisations
- ▸Background in compiler design or hardware architecture
- ▸Familiarity with quantisation-aware training (QAT) and GPTQ/AWQ
TAL Corp is an equal opportunity employer. We believe the best team reflects the full diversity of humanity — because we are building for all of it.
Apply Through Training
At TAL Corp you don't just send a résumé — you prove yourself. Apply by joining our training program; complete it, and top performers are hired into this role.
- 1Register & start your 7-day program
- 2Train, build real skills, earn a credential
- 3Top performers → straight into hiring
Already training? Log in