Member of Technical Staff, Post-Training (India)

About this job

As a Member of Technical Staff, Post-Training at Handshake in India, your daily work involves designing and building advanced post-training systems, evaluation frameworks, and data pipelines for frontier AI models. You will collaborate closely with AI researchers, domain experts, and engineers to tackle complex post-training challenges such as reinforcement learning, supervised fine-tuning, and reward modeling. Handshake works directly with frontier labs to organize expert human knowledge and build the systems that advance the AI economy. Your normal day involves translating open-ended research questions into rigorous experiments, prototyping new evaluation methodologies, running fast iteration loops, and turning successful prototypes into reusable, production-quality platforms. Early members of this team have significant ownership and influence over the technical direction and operating culture.

Responsibilities

• Design post-training systems and methodologies like supervised fine-tuning, reinforcement learning, preference optimization, and reward modeling.
• Translate open-ended research or partner needs into clear hypotheses, experiments, evaluation plans, and production-quality implementations.
• Build and improve evaluation frameworks, benchmarks, training environments, data-processing pipelines, and quality-control systems.
• Run fast, rigorous iteration loops to prototype, evaluate, interpret results, and turn learnings into next-generation systems or products.
• Partner directly with AI researchers and domain experts to develop high-signal data, feedback, and evaluation methods.
• Identify repeatable patterns across engagements and productize them into reusable software and platforms.
• Raise the technical bar through strong design judgment, clear communication, code quality, and mentorship.

Requirements

• 3+ years of demonstrated strength in post-training, fine-tuning, or model-evaluation work including RL, SFT, LoRA/PEFT, or RLHF.
• Strong Python skills and the ability to write clean, efficient, and scalable software.
• Hands-on experience with modern ML tooling, particularly PyTorch and large-scale data, training, or evaluation workflows.
• Sound experimental judgment to form hypotheses, choose meaningful metrics, diagnose failures, and distinguish signal from noise.
• Experience designing systems with the ability to make tradeoffs around quality, scale, reliability, and reuse.
• Comfort operating in an ambiguous, fast-moving environment with substantial ownership.
• Collaborative, low-ego communication to work effectively with researchers, engineers, domain experts, and customers.

Good to have

• Building or operating large-scale ML training, inference, data, or evaluation systems.
• Developing LLM/agent benchmarks, evaluation methodologies, annotation systems, or data-quality frameworks.
• Research or applied work on reinforcement learning, alignment, model behavior, synthetic data, or human-in-the-loop systems.
• Published research, meaningful open-source contributions, or evidence of technical leadership in ML systems or AI research.
• Experience productizing research or repeated customer work into robust, reusable platforms.

Who should apply

This role suits experienced builders and researchers with a strong background in machine learning engineering, research science, or research engineering who thrive in ambiguous, fast-moving environments. If you have at least three years of hands-on experience in post-training, fine-tuning, or model evaluation and want to shape an early technical organization in India, this position is a great fit. It requires a builder's mindset, solid Python skills, and the ability to reason deeply about model improvement.

Frequently asked questions