LLM Evaluation Lead (Applied Scientist)

Tekskills Inc.; Kolkata District; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

Tekskills Inc. in Kolkata is seeking a Senior Generative AI Engineer with hands-on experience in AI/ML and LLM technologies to design and deploy enterprise Gen AI solutions.

You will lead design efforts, mentor junior engineers, and work with stakeholders to identify AI use cases while ensuring scalability, security, and performance across enterprise workflows.

Qualifications

• Strong hands-on experience with AI/ML and LLM technologies.
• Proven ability to design and deploy Gen AI solutions for enterprises.
• Experience leading teams and mentoring junior engineers.

Responsibilities

• Design and develop Generative AI and LLM-based solutions
• Implement RAG pipelines, AI agents, prompt engineering, and knowledge systems
• Integrate Gen AI models with enterprise applications and workflows
• Lead technical design and mentor junior team members
• Work with stakeholders to identify and implement AI use cases
• Ensure scalability, security, and performance of AI solutions

Skills

LLM basics

Generative AI

RAG pipelines

AI agents

Prompt engineering

Knowledge systems

Leadership

Communication

Mentoring

Tools

Ragas

DeepEval

TruLens

Job description

Job Summary

We are looking for a Senior Generative AI Engineer with strong hands‑on experience in AI/ML and LLM technologies. The role requires excellent communication, leadership skills, and deep coding expertise to build and deploy enterprise Gen AI solutions.

Key Responsibilities

• Design and develop Generative AI and LLM-based solutions
• Implement RAG pipelines, AI agents, prompt engineering, and knowledge systems
• Integrate Gen AI models with enterprise applications and workflows
• Lead technical design and mentor junior team members
• Work with stakeholders to identify and implement AI use cases
• Ensure scalability, security, and performance of AI solutions

Key Skills

• Deep understanding of LLM behavior & failure modes
• Prompt sensitivity, hallucination analysis, RAG failure modes
• Evaluation strategy ownership (offline & online)
• Tools: Ragas, DeepEval, TruLens
• Red‑teaming & adversarial prompt design
• Vendor model comparison tracking
• Bridge between Data Science & Product