GenAI Engineer

Enoves; Lahore; On-site; PKR 350,000 - 700,000; Full time

Job summary

Enoves is seeking a Generative AI Engineer to build, fine-tune, and deploy advanced AI systems in Lahore, Pakistan. You will work with LLMs, RAG architectures, and AI orchestration platforms to solve data parsing, code generation, and automation tasks.

Responsibilities include developing LLM applications with LangChain/LlamaIndex, designing RAG pipelines, fine-tuning models, and delivering low-latency APIs. Proficiency in Python, Node.js/TypeScript, and OpenAI/Anthropic APIs is essential.

Qualifications

• Strong programming skills in Python and familiarity with Node.js/TypeScript.
• Experience with OpenAI APIs, Anthropic APIs, and open-source models (Llama, Mistral).
• Familiarity with Vector Databases and embedding models.
• Understanding of machine learning pipelines, evaluation metrics, and GPU compute environments.
• Ability to write clean, modular, and optimized code.

Responsibilities

• Develop and deploy LLM applications using LangChain, LlamaIndex, or custom workflows.
• Design and optimize Retrieval-Augmented Generation (RAG) pipelines and vector databases (Pinecone, Chroma).
• Fine-tune pre-trained models and optimize prompt engineering strategies.
• Build robust API endpoints to serve AI models with low latency and high availability.
• Stay updated on state-of-the-art AI research and transfer knowledge to product modules.

Skills

Python programming

Node.js/TypeScript

OpenAI APIs

Anthropic APIs

Llama/ML models

Vector databases

Embedding models

ML pipelines

Clean code

Tools

LangChain

LlamaIndex

Pinecone

Chroma

Job description

Enoves is seeking a Generative AI Engineer to build, fine-tune, and deploy advanced artificial intelligence systems. You will build solutions leveraging LLMs, RAG architectures, agentic flows, and AI orchestration platforms to solve complex data parsing, code generation, and automation workflows.

Responsibilities:

• Develop and deploy LLM applications using LangChain, LlamaIndex, or custom workflows.
• Design and optimize Retrieval-Augmented Generation (RAG) pipelines and vector databases (Pinecone, Chroma).
• Fine-tune pre-trained models and optimize prompt engineering strategies.
• Build robust API endpoints to serve AI models with low latency and high availability.
• Stay updated on state-of-the-art AI research and transfer knowledge to product modules.

Requirements:

• Strong programming skills in Python and familiarity with Node.js/TypeScript.
• Experience working with OpenAI APIs, Anthropic APIs, and open-source models (Llama, Mistral).
• Familiarity with Vector Databases and embedding models.
• Understanding of machine learning pipelines, evaluation metrics, and GPU compute environments.
• Ability to write clean, modular, and optimized code.