Prompt Engineer

Role: Lead Prompt Engineer

Domain: Insurance & Underwriting (Must required)

Job Overview

We are looking for highly motivated Lead Prompt Engineers to join our AI team and work on building and optimizing large-scale document intelligence systems. This role involves designing, testing, and continuously improving prompts and AI workflows to extract, structure, and validate data from complex, unstructured documents. You will work closely with AI engineers, domain experts, and product teams to ensure high accuracy, consistency, and scalability of AI-driven outputs.

Key Responsibilities

• Design, develop, and optimize prompts for LLM-based workflows (extraction, QA, validation)

• Work on field-level extraction logic across complex documents (PDFs, emails, Excel, etc.)

• Analyse model outputs and identify failure patterns, edge cases, and inconsistencies

• Continuously improve prompt accuracy through iterative testing and refinement

• Collaborate with domain experts to understand business context and data nuances

• Support confidence calibration and validation logic

• Contribute to building reusable prompt templates and libraries

• Work with structured outputs (JSON, tables, schemas)

• Assist in integrating feedback loops (human-in-the-loop corrections, RLAIF)

• Document prompt strategies, assumptions, and improvements

Must-Have Skills Technical

• Bachelor of Engineering 7+ years experience
• Led a team to successfully deliver projects within schedule and quality expectations.
• Managed task assignments, workload balancing, and resource planning.
• Collaborated with stakeholders to define priorities and resolve operational challenges.
• Improved team productivity through process optimization and continuous improvement initiatives.
• Mentored team members and supported their professional growth and skill development.

• Strong understanding of LLMs and prompt engineering concepts

• Ability to work with: JSON, structured outputs, schema-driven extraction

• Strong analytical skills to debug model outputs

• Familiarity with: Prompt chaining, Context management, Few-shot / zero-shot techniques Problem-Solving & Thinking

• Ability to break down ambiguous requirements into structured logic • Strong attention to detail (critical for extraction accuracy)

• Pattern recognition across different document formats

• Ability to handle edge cases and exceptions Communication & Collaboration

• Clear communication of issues, findings, and improvements

• Ability to work with: AI engineers, Domain experts, Product teams

• Comfortable documenting learnings and prompt strategies

Nice-to-Have Skills

• Experience with: LangChain / LlamaIndex / similar frameworks

• Basic Python knowledge (for testing / scripting)

• Exposure to: Document processing (OCR, PDFs, etc.)

• Understanding of: Insurance domain (underwriting, claims, SOV, loss runs)

• Familiarity with: Evaluation metrics (accuracy, precision, recall, confidence)

• Experience with: Annotation / labeling tools

Location: Bangalore, India (Open for relocation to Bangalore after few months)