Prompt / LLM Engineer

LETITBEX AI; Hyderabad; On-site; INR 1,000,000 - 1,500,000; Full time

Job summary

LETITBEX AI, based in Hyderabad, is looking for a Prompt / LLM Engineer with 3–5 years' experience. The role entails specializing in designing and optimizing prompts for various products, conducting experimentation, and collaborating with teams on LLM integration.

The ideal candidate should have deep hands-on experience with LLMs and strong skills in prompt engineering techniques. Additional experience with RAG systems and NLP concepts is beneficial, making this an exciting opportunity in AI product development.

Qualifications

• 3–5 years of experience in AI/ML engineering or AI product development.
• Deep hands-on experience with LLMs (GPT-4, Claude, LLaMA, etc.).
• Strong understanding of prompt engineering techniques and evaluation methodologies.

Responsibilities

• Design and optimize prompts for LLM-based tasks related to various products.
• Conduct systematic experimentation to evaluate prompt performance and quality.
• Implement prompt versioning and A/B testing frameworks.

Skills

LLMs experience (GPT-4, Claude, LLaMA)

Prompt engineering techniques

Python proficiency

Analytical skills

Communication skills

Job description

LetitbexAI is a fast‑growing AI‑driven technology company focused on building intelligent, scalable, and enterprise‑grade solutions. We work at the intersection of AI, data engineering, cloud, and business transformation, helping organizations unlock real value from artificial intelligence.

Position

Prompt / LLM Engineer

Experience

3–5 years

Notice Period

Up to 15 days

Role Summary

Specialize in designing, optimizing, and evaluating prompts for LLMs in various products. Build frameworks for systematic prompt engineering and ensure high‑quality LLM outputs for various tasks.

Key Responsibilities

• Design and optimize prompts for LLM‑based tasks related to various products.
• Conduct systematic experimentation to evaluate prompt performance and quality.
• Implement prompt versioning and A/B testing frameworks.
• Build evaluation rubrics and quality metrics for LLM outputs.
• Implement Retrieval Augmented Generation (RAG) patterns for contextual accuracy.
• Collaborate with product and engineering teams on LLM integration and deployment.
• Document prompt strategies, patterns, and best practices.
• Research and evaluate new LLM models and APIs for applications to be developed.
• Manage cost optimization and latency improvements for LLM usage.

Required Skills & Experience

• 3–5 years of experience in AI/ML engineering or AI product development.
• Deep hands‑on experience with LLMs (GPT‑4, Claude, LLaMA, etc.).
• Strong understanding of prompt engineering techniques and evaluation methodologies.
• Experience with LLM APIs and integration patterns.
• Knowledge of NLP concepts and language models.
• Proficiency in Python and ability to work with code‑based prompting frameworks.
• Strong analytical skills and attention to quality.
• Excellent communication and documentation skills.

Nice to Have

• Experience with RAG systems and vector databases.
• Knowledge of fine‑tuning LLMs for specific domains.
• Experience in HR tech domain & Vendor Management Systems.
• Published research or case studies on prompt engineering.
• Experience with LangChain, LlamaIndex, or similar frameworks.