Prompt Engineering Specialist

Rubiscape; Pune District; On-site; INR 400,000 - 700,000; Full time

Job summary

Rubiscape is building a DecisionIntelligence Platform in India, seeking a Prompt Engineering Specialist to design, test, and iterate on prompt systems powering internal LLM agents across BFSI, manufacturing, and healthcare domains.

You will work with production-grade LLMs, tackle enterprise complexity, and contribute to libraries and evaluation frameworks that accelerate software delivery and AI insights for customers.

Qualifications

• 3+ years of hands-on experience in prompt engineering, NLP engineering, or applied LLM development with a production portfolio.
• Deep practical knowledge of major LLM APIs including token economics, context window management, and structured output techniques.
• Experience building prompt evaluation pipelines with automated test harnesses or LLM-as-judge patterns.

Responsibilities

• Design, write, and refine prompt templates for internal LLM agents across code generation, spec interpretation, and enterprise domain reasoning tasks.
• Build and maintain a structured prompt library, versioned and annotated by task type, model, and domain context.
• Develop prompt evaluation frameworks, define metrics, run A/B tests, document performance regressions and improvements.

Skills

Prompt engineering

LLM APIs knowledge

Python scripting

LangChain / LlamaIndex

Enterprise domain reasoning

Education

B.E./B.Tech in CS/AI/ML or Linguistics

Tools

OpenAI GPT-4 API

Anthropic Claude API

Google Gemini API

LangChain

LlamaIndex

Job description

Rubiscape is building the DecisionIntelligence Platform that India’s enterprises will run on for the next decade— and prompt engineering is the craft layer that makes our AI-first developmentworkflows reliable at scale. As a Prompt Engineering Specialist, you willdesign, test, and iterate on the prompt systems that power Rubiscape’s internalLLM agents: from code generation and spec parsing to enterprise domainreasoning across BFSI, manufacturing, and healthcare verticals. You will workwith real production LLMs, real enterprise complexity, and real performanceconstraints — building prompt libraries and evaluation frameworks that directlyaccelerate how Rubiscape ships software and how our platform surfaces AIinsights to customers.

Key Responsibilities

• Design, write, and iterativelyrefine prompt templates for internal LLM agents covering code generation, specinterpretation, code review, documentation, and enterprise domainreasoningtasks.
• Build and maintain a structuredprompt library: versioned, tested, and annotated prompts organised by tasktype, model target, and domain context (BFSI, manufacturing, healthcare, etc.).
• Develop prompt evaluationframeworks: define success metrics, construct test sets, run A/B comparisons,and document prompt performance regressions and improvements.
• Collaborate with SpecEngineering and AI Toolchain teams to ensure prompts are correctlyparameterised by upstream specs and that outputs meet downstream code qualitystandards.
• Investigate and mitigatefailure modes in LLM outputs: hallucination, instruction drift, context loss,and domain-specific reasoning errors relevant to enterprise data and analyticsworkflows.
• Stay current with advances inprompt engineering techniques (chain-of-thought, retrieval-augmentedgeneration, structured output forcing, tool use) and adapt internal practicesaccordingly.
• Document prompt designdecisions, rationale, and empirical results in a shared knowledge baseaccessible to the entire engineering organisation.

Nice to Have

• Experience withretrieval-augmented generation (RAG) architectures and vector databases(Pinecone, Weaviate, pgvector) in enterprise contexts.
• Familiarity with the dataengineering, BI, or analytics domain — ability to write prompts that reasoncorrectly about SQL, data pipelines, ML model outputs, or business KPIs.
• Prior work on multi-agent LLMsystems where prompt design affects agent-to-agent communication and taskdecomposition.
• Contributions to open-sourceprompt engineering toolkits, evaluation frameworks, or published benchmarks.

About Rubiscape

Rubiscape is India’s leading DecisionIntelligence Platform, unifying data engineering, BI, machine learning, andagentic AI in a single governed platform. Built in Pune and trusted by Fortune500 enterprises across BFSI, manufacturing, healthcare, and government. 8international innovation patents. 10 Industry-Academia Labs & COEs. From BIto AI — One Platform. Every Decision.

Requirements

• 3+ years of hands-on experiencein prompt engineering, NLP engineering, or applied LLM development, with a demonstrable portfolio of production prompt systems.
• Deep practical knowledge ofmajor LLM APIs (OpenAI GPT-4/o series, Anthropic Claude, Google Gemini)including token economics, context window management, and structured outputtechniques.
• Experience building promptevaluation pipelines: automated test harnesses, LLM-as-judge patterns, or humanevaluation workflows.
• Strong Python skills forscripting prompt experiments, parsing LLM outputs, and integrating withLangChain, LlamaIndex, or equivalent orchestration frameworks.
• Ability to reason clearly aboutenterprise domain complexity and encode that domain knowledge into reliable,reusable prompt structures.
• B.E. / B.Tech in ComputerScience, AI/ML, or Linguistics; or equivalent practical experience with a strong portfolio.