AI/ML Engineer

Agentic Global Talent; Lahore; On-site; PKR 1,800,000 - 3,200,000; Full time

Job summary

Agentic Global Talent is seeking a hands-on AI Engineer with 3-4 years of experience to join our growing AI team. This role focuses on building and productionizing Generative AI, LLM, and agentic AI applications, with emphasis on turning experiments into deployable systems.

You will work on RAG systems, AI agents, tool calling, memory, and multi-step reasoning, integrating foundation models via Bedrock or Azure OpenAI, and applying best practices for evaluation, safety, and scalable inference.

Qualifications

• Hands-on experience taking AI solutions from experimentation to production.
• Strong Python skills and practical AI deployment experience.
• Familiarity with RAG, embeddings, vector search, and semantic retrieval.

Responsibilities

• Design and develop production-grade Generative AI and LLM applications.
• Build RAG systems, AI agents, copilots, and automation workflows.
• Develop agentic systems with tool calling, planning, memory, and multi-step reasoning.
• Integrate foundation models via Bedrock and/or Azure OpenAI.
• Evaluate models for accuracy, latency, and cost.
• Implement prompt engineering and context management strategies.
• Implement embeddings, semantic retrieval, and vector search for RAG apps.
• Design AI evaluation frameworks covering quality, safety, latency, and cost.
• Implement guardrails and human-in-the-loop mechanisms.
• Fine-tune/adapt models with LoRA/PEFT.
• Build scalable inference services and production APIs.
• Monitor and continuously improve prompts and AI behavior.
• Collaborate with Product and Software teams to translate requirements into AI features.

Skills

Python

LLMs

Generative AI

RAG

Prompt engineering

AI testing

Tool-calling

Education

Bachelor’s degree in CS/AI/ML/Engineering

Tools

LangChain

LangGraph

LlamaIndex

Bedrock

Azure OpenAI

OpenAI API

PyTorch

Transformers

Job description

About This Role.

We are looking for a hands-on AI Engineer with 3-4 years of experience to join our growing AI team. This role is focused specifically on building and productionizing Generative AI, LLM, and agentic AI applications.

The ideal candidate has strong Python skills and practical experience taking AI solutions from experimentation and prototyping through evaluation, deployment, monitoring, and continuous improvement.

Key Responsibilities

• Design and develop production-grade Generative AI and LLM applications.
• Build RAG systems, AI agents, copilots, and intelligent automation workflows.
• Develop agentic systems involving tool calling, function calling, planning, memory, and multi-step reasoning workflows.
• Integrate foundation models using platforms such as Amazon Bedrock and/or Azure OpenAI.
• Evaluate and select appropriate foundation models based on accuracy, latency, cost, and application requirements.
• Develop advanced prompt engineering and context management strategies.
• Implement embeddings, semantic retrieval, reranking, and vector-search techniques for RAG applications.
• Design AI evaluation frameworks covering response quality, hallucination, groundedness, relevance, safety, latency, and cost.
• Implement AI guardrails, responsible AI controls, and human-in-the-loop mechanisms.
• Fine-tune or adapt models where appropriate using techniques such as LoRA/PEFT.
• Build scalable inference services and APIs for integrating AI capabilities into production applications.
• Monitor production AI systems and continuously improve prompts, retrieval strategies, models, and agent behavior.
• Collaborate with Product and Software Engineering teams to translate business requirements into reliable AI-powered product capabilities.

Required Skills

• Strong programming skills in Python.
• Hands-on experience building applications using LLMs and Generative AI.
• Strong understanding of RAG, prompt engineering, embeddings, vector search, and semantic retrieval.
• Experience building AI agents and tool/function-calling workflows.
• Experience with frameworks such as LangChain, LangGraph, LlamaIndex, or similar.
• Experience with Amazon Bedrock, Azure OpenAI, OpenAI APIs, or similar foundation-model platforms.
• Experience with PyTorch, Hugging Face Transformers, or similar AI/ML frameworks.
• Understanding of model inference, evaluation, fine-tuning, and optimization.
• Experience deploying AI applications into production environments.
• Strong understanding of AI safety, security, hallucination mitigation, and responsible AI practices.
• Strong problem-solving, experimentation, communication, and collaboration skills.

Qualification

• Bachelor’s degree in Computer Science, Artificial Intelligence, Machine Learning, Engineering, or a related field.

Experience

• 3-4 years of experience in AI/ML Engineering or a related software-focused AI role.