About this role
At Zensar, we’re “experience-led everything”. We are committed to conceptualizing, designing, engineering, marketing, and managing digital solutions and experiences for over 130 leading enterprises. We are a company driven by a bold purpose: Together, we shape experiences for better futures. Whether for our clients, our people, or the world around us, this belief powers everything we do. At the heart of our culture is ONE with Client - a set of four core values that reflect who we are and how we work: One Zensar, Nurturing, Empowering, and Client Focus.
Part of the $4.8 billion RPG Group, we’re a community of 10,000+ innovators across 30+ global locations, including Milpitas, Seattle, Princeton, Cape Town, London, Zurich, Singapore, and Mexico City. Explore Life at Zensar and join us to Grow. Own. Achieve. Learn. to be the best version of yourself.
We believe the best work happens when individuality is celebrated, growth is encouraged, and well-being is prioritized. We are an equal employment opportunity (EEO) and affirmative action employer, committed to creating an inclusive workplace. All qualified applicants will be considered without regard to race, creed, color, ancestry, religion, sex, national origin, citizenship, age, sexual orientation, gender identity, disability, marital status, family medical leave status, or protected veteran status. Authoring repository-level context for AI coding agents: instruction files, skills, prompt libraries, and the conventions that make them consistent across many repositories. • Reading and reasoning about unfamiliar production code in at least two languages well enough to describe what it does and why. • Automated documentation and code-comprehension generation across legacy codebases. • Context and retrieval design: what to include, what to exclude, chunking and indexing, grounding agent output in real repository facts. • Strong technical writing for a developer audience, and the discipline to templatize rather than hand-craft each product. • Evidence of measurably improving agent output quality by improving context, not by changing the model.
Nice To Have Exposure to legacy stacks — COBOL in particular — where added application and domain context is what makes agentic work viable. • AST, code-graph or static-analysis tooling used to generate context automatically. • Information architecture or taxonomy background.
Authoring repository-level context for AI coding agents: instruction files, skills, prompt libraries, and the conventions that make them consistent across many repositories. • Reading and reasoning about unfamiliar production code in at least two languages well enough to describe what it does and why. • Automated documentation and code-comprehension generation across legacy codebases. • Context and retrieval design: what to include, what to exclude, chunking and indexing, grounding agent output in real repository facts. • Strong technical writing for a developer audience, and the discipline to templatize rather than hand-craft each product. • Evidence of measurably improving agent output quality by improving context, not by changing the model.
Nice To Have Exposure to legacy stacks — COBOL in particular — where added application and domain context is what makes agentic work viable. • AST, code-graph or static-analysis tooling used to generate context automatically. • Information architecture or taxonomy background.