Model Evaluator @ Austin, TX/Sunnyvale, CA- Hybrid -1+yr
REQUIREMENT Model Evaluator Project Duration: 1 year, with possible extension based on performance Location - Austin, TX/Sunnyvale, CA Work Type - Hybrid ( 3 days office must) Type of Visa - GC/Citizen - Independent Candidates only Technical Skills
- Strong understanding of LLMs, generative AI, and transformer-based architectures.
- Experience with Python, data analysis, and model evaluation frameworks.
- Familiarity with prompt engineering, embeddings, RLHF/RLAIF, and LLM-based scoring methods.
- Experience building evaluation datasets and working with annotation platforms.
- Understanding of safety alignment, bias detection, and adversarial testing.
- Tools & Platforms
- ML/AI frameworks: PyTorch, TensorFlow, HuggingFace, LangChain.
- Evaluation/annotation tools: Scale AI, GroundTruth, Labelbox, Prodigy.
- Prompt testing tools: Weights & Biases, MLflow, OpenAI evals, LLM-as-a-judge pipelines.
Thanks & Regards, John Stanley- Sr. BDM / Delivery Manager Maintec Technologies Inc 8801 Fast Park Drive, Ste. 301, Raleigh, NC 27617 Mobile: +1 (919) 267-1887 / +91- 98411-45549 Email: [email protected]; www.maintec.in | www.maintec.com LinkedIn :www.linkedin.com/in/johnstanley1/ Bangalore | Chennai | Hyderabad | Pune | Noida | USA Apply tot his job Apply To this Job