A

Alok Kumar Yadav

Director of Engineering

Bengaluru, Karnataka, India4 yrs 3 mos experience
AI EnabledAI ML Practitioner

Key Highlights

  • Expert in Reinforcement Learning and Python programming.
  • Led large-scale AI projects enhancing model safety and accuracy.
  • Director-level experience in tech leadership.
Stackforce AI infers this person is a skilled AI engineer with leadership experience in advanced machine learning projects.

Contact

Skills

Core Skills

Reinforcement LearningPython (programming Language)

Other Skills

Prompt EngineeringRLHFStrategy

Experience

Sumyati astro tech llp

Director

Present

Scale ai

Software Engineer

Apr 2024May 2024 · 1 mo · Bengaluru, Karnataka, India · Remote

  • Executed large-scale Reinforcement Learning from Human Feedback (RLHF) workflows for a leading AI data company, focusing on enhancing the safety, accuracy, and helpfulness of next-generation large language models.
  • Contributed production-level Python code to the Bulba + ICE (Implicit Code Execution) project, a novel initiative to improve multi-step reasoning in LLMs through advanced model alignment techniques.
  • Applied advanced prompt engineering techniques and expert-level programming to architect and implement robust solutions for complex model behavior challenges, ensuring superior technical outcomes for enterprise-grade AI systems.
Reinforcement LearningRLHFPython (Programming Language)Prompt Engineering

Amazon

Software Engineer

May 2022Nov 2022 · 6 mos

Rubrik

Software Engineer

Mar 2021Mar 2022 · 1 yr

Flipkart

Software Engineer

Jan 2020Mar 2021 · 1 yr 2 mos

Samsung r&d institute india

Software Engineer

Jun 2017Jan 2019 · 1 yr 7 mos

Practo

Software Engineer Intern

May 2016Jul 2016 · 2 mos

Education

Indian Institute of Technology (Banaras Hindu University), Varanasi

Bachelor of Technology - BTech — Computer Science and Engineering

Kendriya Vidyalaya

Stackforce found 100+ more professionals with Reinforcement Learning & Python (programming Language)

Explore similar profiles based on matching skills and experience