Senior AI Engineer

We are looking for a highly experienced Senior AI Engineer to join our fast-growing AI practice and drive the design, development, and scaling of production-grade agentic applications. This is a hands-on engineering role for someone who thrives at the intersection of applied research and enterprise software delivery, moving from whiteboard to working system and from prototype to production without compromising on quality, reliability, or scalability.

You will work closely with cross-functional teams across our Global Delivery Centres, collaborating with architects, product owners, and client stakeholders to build AI systems that deliver genuine value in production not just in demos.

• →Design, build, and ship multi-agent systems and agentic workflows using frameworks such as LangGraph, Microsoft Agent SDK, AutoGen, or equivalent ecosystems.
• →Architect end-to-end GenAI solutions covering the full lifecycle, from prompt engineering and RAG pipeline design to evaluation, monitoring, and continuous improvement.
• →Lead implementation of robust guardrails (soft constraints such as prompt-level controls, and hard constraints such as output filters and policy enforcement layers) to ensure safety, reliability, and compliance.
• →Build and maintain evaluation frameworks to measure and improve precision, recall, relevance, and response quality of AI systems in production.
• →Apply fine-tuning techniques where applicable, including supervised fine-tuning, RLHF, and parameter-efficient methods (LoRA, QLoRA), to adapt foundation models to domain-specific requirements.
• →Develop and maintain RAG pipelines covering document ingestion, chunking strategies, vector store management, hybrid retrieval, and context window optimization.
• →Integrate agentic systems with enterprise tools, APIs, and data sources through well-designed orchestration and tool-calling layers.
• →Operate effectively in an incubation and rapid-prototyping environment, delivering functional MVPs quickly while engineering with production scalability in mind from day one.
• →Mentor mid-level engineers, conduct code reviews, and contribute to internal AI engineering best practices and reusable accelerators.
• →Engage with client teams to understand requirements, present technical approaches, and translate business problems into agentic AI solutions.

• 6 to 10 years of overall software engineering experience, with at least 3 to 4 years focused on applied AI/ML engineering.
• Proven, hands-on experience building multiple production-grade GenAI applications and not just proofs-of-concept, with demonstrable business impact.
• Strong proficiency with agentic frameworks: LangGraph, LangChain, Microsoft Semantic Kernel, Microsoft Agent SDK, AutoGen, CrewAI, or comparable ecosystems.
• Deep, hands-on understanding of the end-to-end GenAI development lifecycle, including prompt engineering and orchestration, RAG pipeline design and retrieval optimization, and LLM evaluation methodologies (automated evals, human evals, benchmark frameworks).
• Hands-on experience with LLM fine-tuning workflows and model adaptation techniques.
• Experience designing and implementing guardrails, content moderation layers, and response quality controls in production systems.
• Proficiency in Python; working knowledge of cloud AI services (Azure OpenAI, AWS Bedrock, or GCP Vertex AI) and vector databases (Pinecone, Weaviate, pgvector, or similar).
• Experience with multi-agent orchestration patterns including supervisor agents, parallel agents, human-in-the-loop workflows, and agent memory management.
• Strong software engineering fundamentals: system design, API development, CI/CD, and code quality practices.
• Experience with MLOps tooling for LLM systems such as LangSmith, Weights and Biases, MLflow, or similar.
• Familiarity with agentic security considerations including prompt injection, jailbreak mitigation, and data leakage prevention.
• Prior experience in a consulting or professional services environment, managing multiple client engagements simultaneously.
• Exposure to enterprise integration patterns, including connecting AI agents with ERP, CRM, ticketing, or knowledge management systems.
• Contributions to open-source AI projects or published work (technical blogs, conference talks, or research papers).

We have an amazing team of 700+ individuals working on highly innovative enterprise projects & products. Our customer base includes Fortune 100 retail and CPG companies, leading store chains, fast-growth fintech, and multiple Silicon Valley startups.

What makes Confiz stand out is our focus on processes and culture. Confiz is ISO 9001:2015 (QMS), ISO 27001:2022 (ISMS), ISO 20000-1:2018 (ITSM) and ISO 14001:2015 (EMS) Certified. We have a vibrant culture of learning via collaboration and making workplace fun.

People who work with us work with cutting-edge technologies while contributing success to the company as well as to themselves. 

To know more about Confiz Limited, visit: https://www.linkedin.com/company/confiz-pakistan/