Prompt Engineering Specialist

Rubiscape is building the Decision Intelligence Platform that India’s enterprises will run on for the next decade — and prompt engineering is the craft layer that makes our AI-first development workflows reliable at scale. As a Prompt Engineering Specialist, you will design, test, and iterate on the prompt systems that power Rubiscape’s internal LLM agents: from code generation and spec parsing to enterprise domain reasoning across BFSI, manufacturing, and healthcare verticals. You will work with real production LLMs, real enterprise complexity, and real performance constraints — building prompt libraries and evaluation frameworks that directly accelerate how Rubiscape ships software and how our platform surfaces AI insights to customers.

·         Design, write, and iteratively refine prompt templates for internal LLM agents covering code generation, spec interpretation, code review, documentation, and enterprise domain reasoning tasks.

·         Build and maintain a structured prompt library: versioned, tested, and annotated prompts organised by task type, model target, and domain context (BFSI, manufacturing, healthcare, etc.).

·         Develop prompt evaluation frameworks: define success metrics, construct test sets, run A/B comparisons, and document prompt performance regressions and improvements.

·         Collaborate with Spec Engineering and AI Toolchain teams to ensure prompts are correctly parameterised by upstream specs and that outputs meet downstream code quality standards.

·         Investigate and mitigate failure modes in LLM outputs: hallucination, instruction drift, context loss, and domain-specific reasoning errors relevant to enterprise data and analytics workflows.

·         Stay current with advances in prompt engineering techniques (chain-of-thought, retrieval-augmented generation, structured output forcing, tool use) and adapt internal practices accordingly.

·         Document prompt design decisions, rationale, and empirical results in a shared knowledge base accessible to the entire engineering organisation.

·         Experience with retrieval-augmented generation (RAG) architectures and vector databases (Pinecone, Weaviate, pgvector) in enterprise contexts.

·         Familiarity with the data engineering, BI, or analytics domain — ability to write prompts that reason correctly about SQL, data pipelines, ML model outputs, or business KPIs.

·         Prior work on multi-agent LLM systems where prompt design affects agent-to-agent communication and task decomposition.

·         Contributions to open-source prompt engineering toolkits, evaluation frameworks, or published benchmarks.

Rubiscape is India’s leading Decision Intelligence Platform, unifying data engineering, BI, machine learning, and agentic AI in a single governed platform. Built in Pune and trusted by Fortune 500 enterprises across BFSI, manufacturing, healthcare, and government. 8 international innovation patents. 10 Industry-Academia Labs & COEs. From BI to AI — One Platform. Every Decision.

·         3+ years of hands-on experience in prompt engineering, NLP engineering, or applied LLM development, with a demonstrable portfolio of production prompt systems.

·         Deep practical knowledge of major LLM APIs (OpenAI GPT-4/o series, Anthropic Claude, Google Gemini) including token economics, context window management, and structured output techniques.

·         Experience building prompt evaluation pipelines: automated test harnesses, LLM-as-judge patterns, or human evaluation workflows.

·         Strong Python skills for scripting prompt experiments, parsing LLM outputs, and integrating with LangChain, LlamaIndex, or equivalent orchestration frameworks.

·         Ability to reason clearly about enterprise domain complexity and encode that domain knowledge into reliable, reusable prompt structures.

·         B.E. / B.Tech in Computer Science, AI/ML, or Linguistics; or equivalent practical experience with a strong portfolio.