Senior AI Engineer

Open 20d

Responsibilities:

Design, develop, and deploy AI-powered conversational agents using LLMs (e.g., GPT-4, Claude, LLaMA) and frameworks (e.g., LangChain, AutoGen, CrewAI).
Architect end-to-end agent pipelines including memory, tools, planning, retrieval (RAG), and reasoning.
Build multi-agent systems capable of performing complex tasks autonomously (e.g., task orchestration, goal management, agent collaboration).
Optimize agent behavior through prompt engineering, fine-tuning, and reinforcement learning from human feedback (RLHF).
Integrate agents into various interfaces (e.g., web apps, messaging platforms, voice assistants).
Collaborate with cross-functional teams (engineering, design, product) to define conversational UX and improve engagement.
Stay current with the latest advancements in LLMs, agent frameworks, and conversational AI – and incorporate relevant innovations into the stack.
Lead code reviews, mentor junior AI engineers, and help shape the AI roadmap.

Required Skills:

Bachelor’s or Master’s degree in Computer Science, AI, NLP, or related field. PhD a plus.
5+ years of hands-on experience in ML/AI, with at least 2+ years focused on LLMs, chatbots, or AI agents.
Strong proficiency in Python and libraries such as LangChain, Hugging Face Transformers, OpenAI SDK, or similar.
Deep understanding of LLMs, prompt engineering, vector databases (e.g., Pinecone, FAISS), and RAG pipelines.
Experience building production-grade chatbot or AI assistant systems.
Strong understanding of dialogue systems, context management, and personalization.
Familiarity with cloud-based ML platforms (AWS/GCP/Azure), containerization (Docker), and APIs.

Benefits:

Position: Onsite

Timing: Night Shift Only

Location: The Enterprise Building, Multan Road, Near Thokar