Applied AI Engineer

Location : Hyderabad, India

Employment Type : Full-Time

Experience : 4 - 11 Years

About InfoMagnus :

InfoMagnus is building the next generation of enterprise AI solutions through our Precision AI Framework, a comprehensive approach that combines methodologies, software accelerators, governance, and platforms to maximize business value from Applied AI.

As an Applied AI Engineer, you'll work alongside AI Architects and global consulting teams to design and build production-grade AI systems for enterprise customers. This is a hands-on engineering role where you'll leverage cutting-edge LLM technologies, agentic AI frameworks, AI-assisted development tools, and modern cloud platforms to deliver scalable, secure, and observable AI solutions.

About the Role :

We're looking for engineers who love building production AI systems, not just prototypes.

You'll develop enterprise-grade AI applications powered by Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), agentic workflows, and modern AI infrastructure. Working in an AI-native engineering environment, you'll use tools such as GitHub Copilot, Claude Code, Cursor, LangChain, CrewAI, LangGraph, and OpenAI Agents SDK to accelerate development and deliver robust, production-ready solutions.

Key Responsibilities :

1. AI Application Development :

- Design, develop, and deploy LLM-powered applications using LangChain, LlamaIndex, Semantic Kernel, and similar frameworks.

- Build Retrieval-Augmented Generation (RAG) pipelines using vector databases such as Pinecone, Qdrant, Milvus, or pgvector.

- Develop conversational AI, AI assistants, and multi-agent systems using CrewAI, LangGraph, or OpenAI Agents SDK.

- Implement prompt engineering strategies, tool calling, function calling, and workflow orchestration.

- Build reusable AI accelerators, templates, and components aligned with the Precision AI Framework.

2. AI-Augmented Engineering :

- Use GitHub Copilot, Claude Code, Cursor, or similar AI coding assistants as part of your daily development workflow.

- Drive AI-assisted software development practices, including automated testing, AI-powered code reviews, and intelligent CI/CD automation.

- Evaluate emerging AI engineering tools and establish engineering best practices.

3. Data Engineering & AI Infrastructure :

- Build enterprise data pipelines supporting AI workloads.

- Develop embedding pipelines, chunking strategies, metadata enrichment, and retrieval optimization.

- Deploy AI applications on AWS, Azure, or GCP using Docker, Kubernetes, and Infrastructure as Code (Terraform, CDK, or Pulumi).

- Implement MLOps practices including experiment tracking, model versioning, evaluation, and deployment automation.

4. Observability, Governance & Security :

- Implement AI observability using OpenTelemetry, LangSmith, Langfuse, Arize Phoenix, or similar platforms.

- Build governance capabilities including guardrails, policy enforcement, audit logging, and compliance automation.

- Apply AI security best practices including prompt injection protection, PII handling, secrets management, and secure model access.

5. Collaboration & Delivery :

- Work closely with AI Architects and consulting teams throughout the solution lifecycle.

- Participate in architecture discussions, code reviews, sprint planning, and technical design sessions.

- Create technical documentation, deployment guides, and operational runbooks.

- Mentor team members and contribute reusable engineering assets.

Required Skills & Experience :

- 4+ years of software engineering experience with at least 2 years building AI/ML or data-intensive applications.

- Strong Python programming skills.

- Hands-on experience with LangChain, LlamaIndex, Semantic Kernel, or equivalent LLM orchestration frameworks.

- Experience integrating OpenAI, Anthropic, Azure OpenAI, or open-source LLMs.

- Strong understanding of prompt engineering, function calling, streaming, and AI workflow design.

- Experience with Retrieval-Augmented Generation (RAG), embeddings, vector databases, and semantic search.

- Hands-on experience using GitHub Copilot, Claude Code, Cursor, or similar AI-assisted development tools.

- Experience deploying containerized applications using Docker and Kubernetes.

- Cloud experience with AWS, Azure, or Google Cloud Platform.

- Infrastructure as Code experience using Terraform, CDK, Pulumi, or equivalent.

- Experience with MLflow, Weights & Biases, Neptune, or similar MLOps platforms.

- Knowledge of observability and monitoring using OpenTelemetry or AI observability platforms.

- Strong communication and technical documentation skills.

Preferred Qualifications :

- Experience building multi-agent AI systems using CrewAI, LangGraph, AutoGen, or OpenAI Agents SDK.

- Experience with ETL/ELT pipelines, Kafka, Flink, Spark, or modern data engineering platforms.

- Knowledge of AI governance, compliance, and responsible AI practices.

- Experience implementing guardrails, prompt injection protection, content filtering, and PII detection.

- Familiarity with React and TypeScript for AI-powered user interfaces.

- Contributions to open-source AI projects or technical publications.

- Consulting or client-facing delivery experience.

- Bachelor's or Master's degree in Computer Science, AI/ML, or a related discipline.

Technology Stack :

- AI Development : GitHub Copilot, Claude Code, Cursor

- LLM Frameworks : LangChain, LlamaIndex, Semantic Kernel

- Agentic AI : CrewAI, LangGraph, OpenAI Agents SDK

- Vector Databases : Pinecone, Qdrant, Milvus, pgvector

- MLOps : MLflow, Weights & Biases, Neptune

- Observability : OpenTelemetry, LangSmith, Langfuse, Arize Phoenix

- Governance & Security : NeMo Guardrails, Lakera Guard, HiddenLayer

- Cloud & Infrastructure : AWS, Azure, GCP, Docker, Kubernetes, Terraform