Senior AI/ML Engineer

Strategic Systems International

Lahore , Pakistan

Apply Now

Posted 2 days ago 19 views Report Job

We are looking for a highly motivated GenAI / LLM Engineer with over three years of experience to join our team. The successful candidate will be responsible for designing, developing, and optimizing advanced generative AI solutions. This role involves hands-on work with end-to-end GenAI systems, including LLM-based applications, prompt engineering pipelines, retrieval-augmented generation (RAG) architectures, and multi-step autonomous agent workflows. The ideal candidate should possess strong problem-solving skills, practical experience with modern AI frameworks, and the ability to integrate APIs, vector databases, and external tools to build scalable and reliable AI systems.

Key Responsibilities

- GenAI Solution Development: Design, develop, and optimize generative AI solutions using large language models such as OpenAI, Claude, and open-source alternatives.
- Prompt Engineering & Optimization: Build and fine-tune prompt engineering pipelines to enhance model performance.
- RAG System Development: Develop retrieval-augmented generation systems that combine external knowledge sources with LLMs.
- Agent Workflow Architecture: Design and implement multi-step agent workflows using orchestration frameworks like LangChain, LangGraph, or similar tools.
- Autonomous Agent Development: Create autonomous agents capable of tool usage, reasoning, and decision-making to perform complex tasks.
- API & Tool Integration: Integrate APIs, vector databases, and external tools seamlessly into agent pipelines to ensure smooth operation.
- Performance Optimization & Debugging: Debug and optimize agent behavior to improve reliability, scalability, and overall system performance.
- Machine Learning Model Development: Develop and deploy machine learning models as needed to support AI solutions.
- Data Processing & Feature Engineering: Conduct data preprocessing, feature engineering, and dataset validation to prepare high-quality inputs for models.
- Embeddings & Vector Database Management: Work extensively with embeddings and manage vector databases such as Milvus, Pinecone, or Weaviate.

Required Qualifications

- Minimum of 3 years of experience in AI/ML development or related software engineering roles.
- Proven hands-on experience building at least one end-to-end GenAI or LLM-based project.
- Familiarity with LangChain, LangGraph, or other LLM orchestration frameworks.
- Strong understanding of large language models, prompt engineering, and retrieval-augmented generation architectures.
- Experience working with REST APIs and microservices.
- Basic knowledge of machine learning fundamentals, including supervised and unsupervised learning techniques.
- Excellent logical reasoning and debugging skills.
- Ability to decompose complex problems into structured, manageable solutions.

Preferred Qualifications and Benefits

While not explicitly listed, candidates with experience in autonomous agent development, advanced prompt optimization, and vector database management will find this role particularly rewarding. We foster a culture of belonging and are committed to diversity and inclusion. As an equal opportunity employer, we strive to create a workplace where every voice is heard, every individual is respected, and everyone has the opportunity to succeed.

This position offers the chance to work on cutting-edge AI technologies in a collaborative environment that values innovation and continuous learning.