Generative AI Engineer

Creuto; Khordha; Sur place; INR 1 200 000 - 1 800 000; Plein temps

Résumé du poste

Creuto is seeking a Generative AI Engineer in India to design and productionize GenAI features across the full stack, from prompt design to LLM orchestration.

You will work on retrieval systems, agentic workflows, and integration of OpenAI/Anthropic/Google APIs, collaborating with product and design to deliver high-value, trustworthy GenAI capabilities.

Qualifications

• 2+ years of software engineering experience.
• Proficient in Python and backend development.
• Experience with GenAI features in production.
• Familiarity with LLM APIs (OpenAI, Anthropic, Google).
• Knowledge of retrieval systems, RAG pipelines, and vector databases.

Responsabilités

• Design and build GenAI features including text generation, summarisation, classification, and Q&A systems.
• Build and maintain RAG pipelines using vector databases.
• Develop agentic workflows and LLM orchestration.
• Integrate LLM APIs into product systems.
• Create evaluation pipelines to monitor quality, reliability and safety.
• Optimize LLM features for latency, cost, and quality in production.
• Collaborate with product and design teams to ship useful, trustworthy GenAI features.
• Monitor GenAI features in production for regressions and unexpected outputs.

Connaissances

Python

LLMs

Generative AI

Backend systems

LangChain

Agentic workflows

Production experience

Outils

Pinecone

Weaviate

Qdrant

pgvector

LangChain

LlamaIndex

Description du poste

Generative AI Engineer

DEPARTMENT

Artificial Intelligence

EMPLOYMENT TYPE

Full Time

LOCATION

India

EXPERIENCE

2 + Years

About the Role

We are looking for a Generative AI Engineer with 2 to 4 years of experience to design and build production-grade generative AI features that create real value for our users. You will work across the full stack of modern GenAI development from prompt design and retrieval systems to agentic workflows and LLM orchestration.

In This Role, You Will

• Design and build GenAI features including text generation, summarisation, classification, and question-answering systems.
• Build and maintain RAG pipelines using vector databases such as Pinecone, Weaviate, Qdrant, or pgvector.
• Develop agentic workflows using frameworks such as LangChain, LlamaIndex, or custom orchestration.
• Integrate LLM APIs from OpenAI, Anthropic, Google, and open-source models into product systems.
• Build evaluation pipelines to continuously measure output quality, reliability, and safety.
• Optimise LLM features for latency, cost, and quality in production environments.
• Work closely with product and design teams to ship GenAI features that are genuinely useful and trustworthy.
• Monitor GenAI features in production for regressions, hallucinations, and unexpected outputs.

You Might Thrive in This Role If You

• Have 2 to 4 years of software engineering experience with at least one year focused on LLMs or generative AI.
• Are proficient in Python and comfortable building backend systems as well as AI pipelines.
• Have shipped at least one GenAI feature in production and can speak to the challenges you solved.
• Think rigorously about output quality and are not satisfied with systems that work in demos but fail in the real world.
• Stay current on the rapidly evolving GenAI tooling landscape and can separate genuine progress from hype.

Bonus If You Have

• Experience fine-tuning or adapting open-source LLMs using LoRA or QLoRA.
• Knowledge of multi-modal systems including vision-language models.
• Familiarity with structured output generation and function calling.
• Experience building multi-agent systems with tool use and memory.