Role Overview :

We are seeking a highly skilled Python AI Engineer to lead the design and development of advanced agentic workflows and large-scale LLM systems.

This role sits at the intersection of AI engineering, prompt operations, evaluation pipelines, and production-grade deployment.

The ideal candidate brings deep expertise in agent-based architectures, LLM evaluation and tracing, MCP-based integrations, and has successfully deployed LLM-powered systems at scale.

You will work closely with product and engineering teams to deliver reliable, enterprise-ready AI solutions.

Key Responsibilities :

Agentic Systems & LLM Engineering :

- Design, develop, and optimize agentic workflows using modern agent frameworks.

- Build multi-step, tool-augmented, and context-aware AI agents for complex use cases.

- Architect MCP (Model Context Protocol) based system integrations for modular and scalable AI solutions.

LLM Evaluation, Tracing & PromptOps :

- Develop and maintain LLM evaluation pipelines, including benchmarking, regression testing, and quality scoring.

- Implement LLM tracing, observability, and debugging workflows to improve reliability and explainability.

- Own prompt engineering and prompt operations, including versioning, testing, optimization, and lifecycle management.

Production Deployment & Scalability :

- Deploy and manage AI/ML and LLM systems in production environments with high availability and performance.

- Design scalable inference architectures supporting latency, throughput, and cost optimization.

- Implement best practices for MLOps, CI/CD, monitoring, and model governance.

Cross-Functional Collaboration :

- Collaborate with product managers, backend engineers, and data teams to translate business requirements into AI solutions.

- Participate in architectural discussions and contribute to AI platform and roadmap decisions.

- Take ownership of features and systems from concept to production and post-deployment support.

Key Result Areas (KRAs):

- Successful delivery of production-grade agentic AI systems

- Reliability and performance of LLM evaluation and tracing pipelines

- Scalability and stability of deployed AI solutions

- Quality and effectiveness of prompt engineering and agent behavior

- Stakeholder satisfaction and cross-team collaboration

Required Skills & Qualifications :

Core Technical Skills :

- Strong proficiency in Python with hands-on experience in AI/ML libraries and frameworks.

- Proven experience with agentic frameworks such as LangChain, LlamaIndex, or similar.

- Hands-on experience with LLM evaluation and observability tools such as LangSmith, Arize, DeepEval, or equivalents.

- Deep understanding of prompt engineering and prompt operations.

- Strong experience deploying and managing AI/ML models in production environments.

Cloud & MLOps :

- Experience with at least one major cloud platform: AWS, Azure, or GCP.

- Solid understanding of MLOps practices, CI/CD pipelines, model monitoring, and versioning.

- Familiarity with containerization and scalable deployment patterns.

Tools & Ways of Working :

- Hands-on experience using GitLab, Trello, Zoom, or similar collaboration and DevOps tools.

- Ability to work independently, take ownership, and drive problems to resolution.

- Comfortable working in fast-paced, high-pressure environments with multiple priorities.

Behavioral & Professional Competencies :

- Strong problem-solving and analytical skills.

- Excellent communication and stakeholder management abilities.

- Self-starter mindset with a strong sense of ownership and accountability.

- Keen interest in continuously learning new AI technologies, business processes, and engineering practices.

Why Join Us :

- Work on cutting-edge LLM and agentic AI systems at scale.

- High ownership role with visibility across product and engineering leadership.

- Opportunity to influence AI architecture, tooling, and best practices.

- Collaborative, innovation-driven engineering culture