Research Engineer, AI Models

About the role

EnCharge AI is building a next‑generation AI platform that dramatically improves compute energy efficiency for inference workloads. We are looking for a Research Engineer to push the boundaries of AI model capability, quality, and efficiency by developing fine‑tuning pipelines, benchmarking frameworks, and hardware‑aware optimisations.

Key responsibilities

• Research and implement state‑of‑the‑art inference acceleration techniques such as quantisation, sparsity, distillation, speculative decoding and caching strategies.
• Partner with hardware, compiler and quantisation teams to translate algorithmic improvements into real gains on our silicon.
• Build profiling tools and comprehensive benchmarking frameworks to identify compute bottlenecks and track quality, latency, throughput and power metrics.
• Develop robust fine‑tuning workflows for modern AI models, experimenting with LoRA, adapters and full fine‑tuning while evaluating new architectures.

Required profile

• 5+ years of experience in ML research, applied ML or ML systems.
• Strong fundamentals in Python and PyTorch.
• Hands‑on experience with transformers, diffusion models and state‑space models.
• Experience fine‑tuning large models and building training/evaluation pipelines.
• Deep understanding of attention mechanisms and optimisation techniques.
• Comfort reading and implementing methods from research papers.

Required skills

• Python
• PyTorch
• Transformers
• Diffusion models
• State‑space models
• LoRA and adapters for fine‑tuning
• Profiling tools (PyTorch Profiler, Nsight)
• Quantisation and hardware‑aware optimisation