Research Engineer, AI Models
New
E
EnCharge AIArtificial Intelligence
India (or Remote-friendly with travel)Full-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 5+ years
- Required Skills
- PythonMachine LearningPyTorch
Requirements
- 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 transformers, attention mechanisms, and optimization techniques.
- Comfort reading and implementing techniques from research papers.
- Experience with efficient inference techniques such as KV cache optimization, attention variants, MoE routing, or flow matching (preferred).
- Background in hardware-aware ML optimization or quantization (preferred).
- Familiarity with profiling tools like PyTorch Profiler or Nsight (preferred).
- Publications in generative modeling, efficient inference, or ML systems (preferred).
- Contributions to open-source ML projects (preferred).
Responsibilities
- Research and implement state-of-the-art techniques to accelerate AI inference—quantization, sparsity, distillation, speculative decoding, caching strategies, and architectural modifications.
- Systematically characterize tradeoffs between model quality, latency, throughput, and power consumption to find optimal operating points across different use cases.
- Partner closely with hardware, compiler, and quantization teams to ensure algorithmic improvements translate to real gains on company silicon.
- Identify optimizations aligned with the architecture's strengths to maximize throughput while minimizing power.
- Build profiling tools and comprehensive benchmarking frameworks to measure model quality and track efficiency metrics.
- Build robust fine-tuning workflows for modern AI models, enabling rapid experimentation with LoRA, adapters, and full fine-tuning.
- Evaluate new architectures and implement techniques to inform technical and go-to-market strategy.
View Full Description & ApplyYou'll be redirected to the employer's site
