DE&A - AIML - Data Science - Artificial Intelligence of Things (AIOT)

Role Summary

We are looking for an experienced Generative AI Engineer to design, develop, and deploy scalable AI solutions using Large Language Models, retrieval-augmented generation, AI agents, and cloud-native technologies.

The ideal candidate should have strong experience in Python, machine learning, natural language processing, prompt engineering, vector databases, and LLM application frameworks. The candidate will collaborate with product managers, architects, data engineers, security teams, and business stakeholders to translate enterprise use cases into secure, reliable, and production-ready Generative AI solutions.

Key Responsibilities

Generative AI Solution Development

• Design, develop, and deploy enterprise-grade Generative AI applications using Large Language Models.
• Build conversational assistants, enterprise search solutions, document intelligence applications, summarization tools, recommendation systems, and content-generation solutions.
• Develop retrieval-augmented generation pipelines using structured and unstructured enterprise data.
• Integrate LLMs with internal applications, databases, APIs, knowledge repositories, and external systems.
• Implement intelligent workflows using AI agents, tools, memory, planning, and orchestration frameworks.
• Develop reusable components and accelerators for prompt management, document ingestion, retrieval, model integration, and response generation.

LLM and Prompt Engineering

• Design, test, and optimize prompts for accuracy, consistency, relevance, and safety.
• Implement zero-shot, few-shot, chain-of-thought, structured output, and tool-calling techniques where appropriate.
• Compare and evaluate commercial and open-source language models based on quality, latency, context length, security, and cost.
• Implement model routing and fallback mechanisms based on business requirements.
• Apply fine-tuning, parameter-efficient fine-tuning, or instruction tuning when prompt engineering and retrieval techniques are insufficient.
• Maintain prompt templates, model configurations, and evaluation criteria through version-controlled repositories.

Retrieval-Augmented Generation

• Build end-to-end document ingestion and retrieval pipelines.
• Process PDF, Word, HTML, text, image, and structured data sources.
• Implement document parsing, chunking, metadata enrichment, embedding generation, indexing, and retrieval.
• Develop semantic, keyword, hybrid, and metadata-based search capabilities.
• Implement reranking, query expansion, contextual compression, grounding, and citation generation.
• Optimize retrieval quality by evaluating chunk size, overlap, embedding models, filters, and ranking strategies.

Agentic AI Development

• Design AI agents capable of reasoning, planning, tool usage, and multi-step execution.
• Develop single-agent and multi-agent workflows for enterprise business processes.
• Integrate agents with enterprise APIs, databases, workflow systems, and automation platforms.
• Implement human-in-the-loop approvals for sensitive or high-impact actions.
• Establish execution limits, access controls, auditability, and failure-handling mechanisms.
• Evaluate agent performance, reliability, tool-selection accuracy, and task-completion rates.

Model Evaluation and Responsible AI

• Develop evaluation frameworks for relevance, groundedness, faithfulness, completeness, toxicity, bias, and hallucination.
• Create benchmark datasets and automated test suites for Generative AI applications.
• Perform model and prompt regression testing before production releases.
• Implement guardrails for input validation, output filtering, prompt injection, sensitive data exposure, and unsafe content.
• Ensure AI solutions comply with enterprise security, privacy, regulatory, and responsible AI requirements.
• Monitor applications for model drift, retrieval degradation, unexpected behavior, and quality issues.

Cloud and Production Deployment

• Deploy Generative AI applications using cloud-native services and containerized environments.
• Build APIs and microservices using Python-based application frameworks.
• Implement continuous integration and continuous deployment pipelines for AI applications.
• Establish observability for model requests, token usage, latency, errors, retrieval performance, and user feedback.
• Optimize infrastructure and application design for scalability, reliability, performance, and cost.
• Troubleshoot production issues across models, prompts, retrieval pipelines, APIs, and cloud services.

Stakeholder Collaboration

• Work with business stakeholders to identify and prioritize high-value Generative AI use cases.
• Translate business requirements into technical architecture and implementation plans.
• Collaborate with solution architects, data engineers, machine learning engineers, QA engineers, and cybersecurity teams.
• Conduct technical demonstrations, proof-of-concept implementations, and stakeholder presentations.
• Document solution architecture, model decisions, prompt strategies, evaluation results, risks, and operational procedures.
• Mentor junior engineers and support the adoption of Generative AI engineering best practices.

Required Technical Skills

Programming and AI

• Strong proficiency in Python.
• Strong understanding of machine learning, deep learning, natural language processing, and neural networks.
• Hands-on experience developing applications using Large Language Models.
• Experience with prompt engineering, embeddings, semantic search, and retrieval-augmented generation.
• Experience integrating models through APIs and software development kits.
• Knowledge of transformer architectures, tokenization, context windows, attention mechanisms, and model inference.

LLMs and AI Platforms

Hands-on experience with one or more of the following:

• Azure OpenAI
• OpenAI APIs
• Google Gemini and Vertex AI
• Anthropic Claude
• Amazon Bedrock
• Hugging Face
• Llama, Mistral, or other open-source models

GenAI Frameworks

Experience with one or more of the following:

• LangChain
• LangGraph
• LlamaIndex
• Semantic Kernel
• AutoGen
• CrewAI
• Haystack

Vector Databases and Search

Experience with one or more of the following:

• Azure AI Search
• Pinecone
• Weaviate
• Milvus
• Chroma
• FAISS
• Elasticsearch or OpenSearch
• PostgreSQL with pgvector

Application Development

• Experience building REST APIs using FastAPI, Flask, or similar frameworks.
• Working knowledge of SQL and NoSQL databases.
• Experience with JSON, APIs, microservices, authentication, and authorization.
• Familiarity with user-interface technologies such as React, Angular, or Streamlit is preferred.

Cloud and DevOps

• Experience with Azure, AWS, or Google Cloud Platform.
• Experience with Docker and containerized application deployment.
• Familiarity with Kubernetes and serverless architectures.
• Experience with Git, CI/CD pipelines, automated testing, and infrastructure-as-code practices.
• Knowledge of monitoring, logging, application telemetry, and cost-management techniques.

Required Qualifications

• Bachelor’s or master’s degree in Computer Science, Artificial Intelligence, Data Science, Information Technology, Engineering, or a related discipline.
• 5 or more years of experience in software engineering, data science, machine learning, or AI engineering.
• At least 2 years of hands-on experience developing Generative AI or LLM-based solutions.
• Demonstrated experience taking AI applications from proof of concept to production.
• Strong understanding of software engineering principles, design patterns, testing, and secure development.
• Strong analytical, problem-solving, and debugging abilities.
• Excellent verbal and written communication skills.

Preferred Qualifications

• Experience delivering enterprise-scale Generative AI solutions.
• Experience implementing agentic AI and multi-agent workflows.
• Knowledge of multimodal AI involving text, image, audio, or video inputs.
• Experience with model fine-tuning, LoRA, QLoRA, quantization, or model compression.
• Understanding of GPU infrastructure, inference optimization, and model-serving platforms.
• Experience with MLflow, Kubeflow, Azure Machine Learning, or similar MLOps platforms.
• Familiarity with data governance, model governance, privacy, and regulatory compliance.
• Experience working in retail, e-commerce, supply chain, marketing, customer service, or enterprise operations.
• Relevant certifications in AI, machine learning, data engineering, or cloud technologies.

Key Competencies

• Strong analytical and problem-solving skills
• Product-oriented AI engineering mindset
• Ability to convert ambiguous business requirements into technical solutions
• Strong focus on security, reliability, and responsible AI
• Effective communication with technical and non-technical stakeholders
• Ability to work in Agile and cross-functional environments
• Continuous learning and adoption of emerging AI technologies
• Strong ownership and production-support mindset

Key Deliverables

• Production-ready Generative AI applications
• Retrieval-augmented generation pipelines
• AI agents and automated enterprise workflows
• Prompt templates and prompt-management standards
• Model and retrieval evaluation frameworks
• Responsible AI guardrails and security controls
• Technical architecture and design documentation
• Monitoring, observability, and operational dashboards
• Reusable GenAI components and engineering accelerators

Success Measures

• Improvement in response relevance, groundedness, and accuracy
• Reduction in hallucinations and unsupported responses
• Achievement of defined latency and availability targets
• Adoption and usage of deployed AI solutions
• Reduction in manual effort or process cycle time
• Compliance with privacy, security, and responsible AI standards
• Controlled token consumption and infrastructure costs
• Successful deployment and operation of AI solutions in production

JD improvements

• Scope: Covers the complete GenAI lifecycle, from use-case definition to production monitoring.
• Technical depth: Includes LLMs, RAG, vector databases, agentic AI, cloud, LLMOps, and security.
• Hiring clarity: Separates mandatory skills, preferred qualifications, deliverables, and measurable outcomes.
• Enterprise readiness: Emphasizes governance, responsible AI, observability, cost control, and production reliability.