What you get to do in this role:

• Design, implement, and optimize LLM pipelines using frameworks such as LangChain, LangGraph, and vendor APIs (OpenAI, Anthropic, etc.).
• Write clean, efficient, and scalable code in Python and Java, applying best practices in ML engineering and enterprise application development.
• Develop and refine prompt engineering strategies and agent reasoning workflows to improve accuracy and reliability.
• Build and maintain evaluation frameworks for measuring model performance, including custom metrics for agent instructions and reasoning.
• Debug, profile, and optimize inference pipelines for latency and cost efficiency at scale.
• Collaborate closely with product teams to translate business needs into technical implementations.
• Contribute to end-to-end development from prototyping to production deployment in enterprise environments.
• Stay current with the latest advancements in LLMs, Agentic AI, and orchestration frameworks, applying new techniques where beneficial.

Qualifications

To be successful in this role you have:

• Experience in leveraging and critically evaluating AI integration into work processes, decision-making, and problem-solving. This includes using AI-powered tools, automating workflows, analyzing AI-driven insights, and exploring AI’s potential impact on business functions or the industry.
• 4 to 6+ years of hands-on experience designing and building AI/ML pipelines and solutions, with a strong emphasis on scalable, production-grade applications.
• Proficiency in Python (ML libraries and GenAI/LLM frameworks) and Java for enterprise application development and object-oriented design.
• Practical experience with LLM frameworks such as LangChain and LangGraph, as well as leading vendor SDKs and APIs (OpenAI, Anthropic, etc.).
• Strong expertise in prompt engineering and designing agentic reasoning workflows and pipelines.
• Solid understanding of ML evaluation techniques, with hands-on experience implementing model monitoring and metrics.
• Proven ability to debug and optimize inference pipelines for both performance and cost efficiency.
• Strong problem-solving skills with the ability to thrive in fast-paced, agile development environments.
• Nice to have: Contributions to open-source projects, technical blogs, or papers related to LLMs and GenAI.