We are looking for a Senior Prompt Engineer with 5+ years of experience in AI and LLM-driven application development. The role focuses on designing, testing, and optimizing enterprise-level prompts for Generative AI, RAG systems, and agentic AI frameworks.

The ideal candidate should have strong hands-on experience with LLM APIs, vector databases, and multi-agent orchestration frameworks. Expertise in prompt engineering, context design, and output control is required.

Experience with Azure AI services, governance, security, and compliance frameworks is highly preferred. The candidate should be able to balance accuracy, cost, performance, and scalability while working with production AI systems.

KEY RESPONSIBILITIES

Prompt Engineering & LLM Development

• Design, develop, test, and optimize advanced prompt strategies for LLMs such as OpenAI GPT, Claude, LLaMA, Mistral, and Gemini.
• Collaborate with business and functional teams to translate business requirements into effective LLM-driven behaviors.
• Engineer multi-step prompt chains, system prompts, role-based prompts, and meta-prompts for complex reasoning tasks.
• Develop prompt templates using Chain-of-Thought (CoT), Tree-of-Thought (ToT), meta prompting, and few-shot conversational prompting.

Frameworks & Prompt Orchestration

• Build prompt workflows using LangChain, LangGraph, and PromptLayer.
• Develop and maintain prompt orchestration pipelines for RAG systems and agentic AI architectures.
• Work with multi-agent systems using LangChain, CrewAI, and MCP architectures.

RAG & Vector Database Integration

• Design RAG optimized prompts integrated with vector databases such as:

• PostgreSQL

• Redis

• FAISS

• Pinecone

• Chroma

• Implement re-ranking pipelines and retrieval optimization strategies.

Agentic AI & Function Calling

• Implement function calling and schema-enforced prompting using JSON/YAML schemas.
• Build prompts that support tool APIs and automated decision workflows.

Prompt Optimization & Evaluation

• Perform A/B testing, regression testing, and prompt versioning.
• Optimize token usage and context window management to reduce inference cost.
• Tune LLM parameters including temperature, top_p, penalties, and max tokens.

AI Safety & Governance

• Design hallucination-resistant and jailbreak-safe prompts with guardrails.
• Implement PII and PHI masking mechanisms.
• Ensure prompts follow RBAC-based access policies and compliance frameworks.

Production Monitoring

• Monitor prompt drift, response instability, and output quality in production systems.
• Define and track prompt performance KPIs such as:

• Quality

• Latency

• Cost

• Consistency

• Ensure compliance with data governance and security policies.

REQUIRED QUALIFICATIONS

• Bachelor's or Master's degree in Computer Science, Data Science, Mathematics, Statistics, or related field.
• 5+ years of experience in AI / LLM-based application development.
• Strong hands-on experience in prompt engineering for production LLM applications.
• Experience integrating RAG systems with vector databases.
• Hands-on experience with agentic AI frameworks and prompt orchestration systems.
• Strong programming experience in Python with API frameworks such as FastAPI or Flask.
• Understanding of LLM security, hallucination control, and bias mitigation.
• Experience with LLMOps / MLOps tools such as MLflow, LangSmith, Weights & Biases, or PromptLayer.
• Knowledge of data protection and compliance standards such as GDPR, HIPAA, and ISO 27001.
• Strong analytical, communication, and collaboration skills.

PREFERRED QUALIFICATIONS

• Certifications in Azure AI, Generative AI, LLMOps, or Prompt Engineering.
• Experience developing enterprise copilots, AI chatbots, and agentic AI solutions.
• Hands-on experience with PromptOps and LLM lifecycle management.
• Expertise in semantic prompting, context engineering, and RAG systems.
• Experience with LLM evaluation tools such as:

• RAGAS

• TruLens

• DeepEval

• PromptLayer

• Strong knowledge of LLM safety, guardrails, and hallucination mitigation.
• Experience with hybrid model routing and fallback strategies.
• Exposure to large-scale AI systems and regulated industries.

CERTIFICATIONS (PREFERRED)

• Azure AI Fundamentals (AI-900)
• Azure AI Engineer Associate (AI-102)
• Generative AI / Prompt Engineering Certifications