Senior AI/ML Engineer
On-siteLahore, Punjab, Pakistan
Job Summary
Design and optimize GenAI solutions using LLMs, including prompt engineering pipelines, RAG architectures, and multi-step autonomous agent workflows. Build end-to-end systems by integrating APIs, vector databases, and external tools while developing ML models and performing data preprocessing. Debug agent behavior for reliability and scalability, ensuring robust performance across OpenAI, Claude, and open-source models. Manage embeddings and vector databases such as Milvus and Pinecone to support retrieval-augmented generation. Apply strong logical reasoning to break down complex problems into structured solutions within a diverse, inclusive environment.
Required Qualifications
- 3+ years of experience in AI/ML development or related software engineering roles
- Hands-on experience building at least one end-to-end GenAI or LLM-based project
- Experience with LangChain / LangGraph / LLM orchestration frameworks
- Understanding of LLMs, prompt engineering, RAG architectures
- Familiarity with REST APIs and microservices
- Basic knowledge of ML fundamentals (supervised/unsupervised learning)
- Strong logical reasoning and debugging capabilities
- Ability to break down complex problems into structured solutions
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.