Entermind AI Hiring! Full Time AI Engineer in Federal Territory - Ricebowl

ABOUT THE ROLE

We are looking for an experienced AI Engineer to design, build, deploy, and operate production-grade AI applications powered by Large Language Models (LLMs). The ideal candidate has hands-on experience taking AI solutions from prototype to production, with a strong understanding of modern AI infrastructure, Retrieval-Augmented Generation (RAG), evaluation frameworks, observability, and cloud AI platforms.

You will work closely with product managers, software engineers, and platform teams to build scalable, reliable, and secure AI-powered products.

KEY RESPONSIBILITIES:

AI Application Development

• Design, develop, and deploy production-ready AI applications using Large Language Models (LLMs).
• Own the complete AI application lifecycle—from experimentation and development to deployment, monitoring, and continuous improvement.
• Build scalable AI systems capable of handling real-world production traffic with high reliability and low latency.
• Collaborate with cross-functional teams to convert business requirements into AI-powered solutions.

Production AI & LLM Engineering

• Build and optimize Retrieval-Augmented Generation (RAG) pipelines for enterprise use cases.
• Develop robust document ingestion pipelines supporting structured and unstructured data sources.
• Implement embedding pipelines, vector databases, chunking strategies, metadata enrichment, and retrieval optimization.
• Design prompt engineering strategies and optimize prompt performance across different LLMs.
• Fine-tune open-source or proprietary LLMs where appropriate to improve domain-specific performance.
• Optimize inference cost, latency, throughput, and response quality.

AI Infrastructure & Platform Engineering

• Work with cloud AI platforms such as AWS AI/Bedrock, Azure AI Foundry, Google Vertex AI
• Integrate managed AI services with enterprise applications.
• Build scalable inference pipelines and model-serving infrastructure.
• Configure secure access to AI services, APIs, and enterprise data sources.

AI Evaluation & Quality Assurance

• Design and implement automated evaluation frameworks for LLM applications.
• Define and monitor AI quality metrics including Faithfulness, Relevance, Groundedness, Hallucination Detection, Answer Correctness, Latency and Cost Per Request.
• Build offline and online evaluation pipelines.
• Perform A/B testing and continuously improve AI application performance using evaluation insights.

AI Observability & Monitoring

• Implement end-to-end observability for AI systems.
• Monitor Model Performance, Prompt Quality, Retrieval Effectiveness, Token Usage, Latency, Error Rates, Cost, User Feedback.
• Build dashboards, alerts, and monitoring pipelines for production AI applications.
• Identify and troubleshoot production issues affecting AI application quality.

AI Gateway & Optimization

• Implement AI gateways for routing requests across multiple LLM providers.
• Build intelligent fallback mechanisms and model routing strategies.
• Implement semantic caching and response caching to reduce latency and inference costs.
• Optimize token utilization and API usage.

Data Ingestion & Knowledge Systems

• Design scalable ingestion pipelines for enterprise knowledge bases.
• Process PDFs, Office documents, web content, databases, APIs, and other structured/unstructured sources.
• Build data transformation, indexing, and synchronization pipelines.
• Ensure data quality, freshness, and governance within AI systems.

Software Engineering & APIs

• Develop RESTful APIs to expose AI capabilities.
• Integrate AI services with existing enterprise applications.
• Collaborate with frontend developers to build intuitive AI-powered user experiences.
• Follow software engineering best practices, including testing, version control, CI/CD, and code reviews.

DevOps & Cloud Deployment

• Deploy AI applications using modern cloud-native practices.
• Build CI/CD pipelines for AI workloads.
• Manage infrastructure, scalability, security, and production releases.
• Collaborate with DevOps teams to ensure high availability and operational excellence.

MANDATORY QUALIFICATIONS

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or a related field.
• Proven experience building, deploying, and operating at least one production AI application.
• Demonstrated experience monitoring and supporting AI applications in production environments.
• Hands-on experience with AI data ingestion pipelines, AI evaluation frameworks, AI observability and monitoring.
• Experience with at least one major AI cloud platform such as AWS (including Bedrock or SageMaker), Azure AI Foundry, Google Vertex AI.
• Strong understanding of LLM fine-tuning techniques, Production-grade Retrieval-Augmented Generation (RAG), AI caching strategies, AI gateways and model routing, Evaluation methodologies, Observability and monitoring.
• Experience working with vector databases, embeddings, and semantic search.
• Strong software engineering fundamentals with proficiency in Python.
• Experience building and consuming REST APIs.
• Familiarity with Git, CI/CD, containerization, and cloud-native development.

GOOD TO HAVE

• AWS Certified Developer – Associate or higher (or equivalent Azure/GCP certification).
• Experience with cloud infrastructure, Kubernetes, Docker, and infrastructure-as-code.
• Experience deploying AI applications at scale.
• Knowledge of frontend technologies (React, Angular, Vue.js, or similar).
• Experience integrating AI applications with enterprise systems.
• Familiarity with agentic AI frameworks such as LangGraph, AutoGen, CrewAI, Semantic Kernel, or similar.
• Experience with LLMOps tooling such as LangSmith, Arize Phoenix, MLflow, Weights & Biases, Promptfoo, or similar.
• Knowledge of AI security, guardrails, responsible AI, and governance practices.
• Experience optimizing AI systems for cost, latency, scalability, and reliability.

PREFERRED EXPERIENCE

• 2–4+ years of software engineering experience with at least 1 years focused on production AI/LLM applications.
• Experience delivering enterprise-grade AI solutions from proof of concept through production.
• Strong understanding of distributed systems, cloud architecture, and scalable application design.
• Ability to balance AI quality, operational cost, performance, and user experience when designing solutions.