Senior AI Engineer

Job description:

As a Senior AI Engineer, you will independently design, build, deploy, and support production-grade GenAI and agentic AI solutions that integrate large language models (LLMs), retrieval-based patterns, APIs, and enterprise workflows. You will play a hands-on engineering role in delivering scalable, reliable, and maintainable AI-powered product capabilities, while partnering closely with Lead AI Engineers, Team Leads, architects, and cross-functional product teams.

This role is ideal for an engineer with strong technical depth in LLM-powered application development, RAG, Python, SQL, and cloud-native AI delivery, who can independently own complex solution components, contribute to engineering standards, mentor junior engineers, and help operationalize AI systems in real business environments.

Key Responsibilities:

• Design, develop, test, and deploy complex LLM-powered application components and AI-enabled services for enterprise use cases
• Build and optimize retrieval-augmented generation (RAG) pipelines, including document ingestion, chunking, embeddings, retrieval strategies, and response grounding
• Implement agentic AI workflows using orchestration frameworks and reusable design patterns for task execution, tool usage, and context handling
• Develop AI-enabled APIs and backend services using technologies such as Python, FastAPI, Azure Functions, containerized services, and REST-based integration patterns (or equivalent platforms and frameworks)
• Work with Azure OpenAI, Azure AI Studio, Semantic Kernel, LangChain, AutoGen, Azure AI Search, or equivalent tools to build scalable GenAI solutions
• Collaborate with Lead AI Engineers and architects to translate solution designs into robust technical implementations, while providing technical guidance on implementation choices where appropriate
• Integrate AI services with enterprise systems, APIs, workflow platforms, and downstream applications
• Implement logging, tracing, monitoring, and basic operational controls using tools such as Application Insights, OpenTelemetry, Azure Monitor, Datadog, New Relic, or equivalent observability platforms
• Actively contribute to design reviews, code reviews, testing, and release activities to maintain quality, engineering discipline, and implementation consistency
• Contribute to reusable assets such as prompt patterns, orchestration templates, shared components, developer utilities, and engineering accelerators
• Troubleshoot production issues, improve reliability, and support continuous improvement of deployed AI capabilities
• Stay current with advancements in LLM tooling, agent frameworks, prompt engineering, retrieval approaches, and applied AI engineering practices

Required Qualifications:

• 5 to 8+ years of experience in software engineering, AI/ML engineering, or AI solution delivery, including hands-on work in building and deploying intelligent applications
• Hands-on experience with Snowflake, Databricks, or equivalent
• Practical experience delivering GenAI, LLM-powered, or AI-enabled solutions in development, pilot, or production environments
• Strong technical foundation in Python and modern backend engineering patterns, with experience building APIs, services, and application components
• Hands-on experience with LLM platforms and AI development tools such as Azure OpenAI, Azure AI Studio, OpenAI API, AWS Bedrock, Google Vertex AI, Databricks, or equivalent
• Experience working with orchestration frameworks such as Semantic Kernel, LangChain, AutoGen, or equivalent approaches for prompt workflows, tool calling, and agent coordination
• Strong working knowledge of retrieval-augmented generation (RAG), embeddings, vector search, and grounding patterns using platforms such as Azure AI Search, Pinecone, Weaviate, FAISS, or equivalent
• Experience building and deploying cloud-native AI services using tools such as Azure Functions, Azure Container Apps, FastAPI, Docker, GitHub, Azure DevOps, or equivalent engineering and deployment platforms
• Solid understanding of CI/CD, containerization, automated testing, and secure deployment practices for modern AI-enabled applications
• Familiarity with observability and operational tooling such as Application Insights, OpenTelemetry, Azure Monitor, Datadog, or New Relic, or equivalent monitoring platforms
• Experience integrating AI services with REST APIs, enterprise workflows, backend systems, or downstream business applications
• Strong problem-solving skills and ability to translate solution requirements into well-structured technical implementations
• Strong ownership mindset across the full SDLC for assigned features and services, including design, build, testing, deployment, support, and continuous improvement
• Good collaboration and communication skills, with the ability to work effectively with engineers, architects, product owners, and platform teams

Preferred Qualifications:

• Experience implementing agentic AI workflows involving multi-step reasoning, tool orchestration, structured prompting, or reusable workflow patterns
• Exposure to Model Context Protocol (MCP), agent-to-agent (A2A) interaction patterns, or similar approaches to context exchange and distributed agent communication
• Familiarity with Microsoft AI Foundry, Azure Machine Learning, Azure AI / Copilot Studio, or equivalent enterprise AI experimentation and solution development platforms
• Experience with enterprise integrations, including workflow tools, API management layers, business systems, or event-driven architectures
• Experience contributing to reusable GenAI accelerators, prompt libraries, orchestration templates, internal developer tooling, or shared engineering utilities
• Familiarity with AI governance, safety, evaluation, and cost-management practices, including token usage awareness, prompt safety, and quality monitoring
• Working knowledge of TypeScript or C#, in addition to Python, for integration into broader enterprise technology stacks
• Experience operating in a build-own-operate product environment with expectations around supportability, reliability, and iterative enhancement
• Ability to clearly communicate technical decisions, implementation trade-offs, and design considerations to both technical and non-technical stakeholders

Skills

AutoGen, Azure AI Search, FAISS, LLM, LangChain, OpenAI, Pinecone, Python, RAG, Semantic Kernel, Weaviate