AI Engineer (GenAI/Agentic Systems)

Responsibilities:

• Design, build, and operate agentic AI services that orchestrate tools, workflows, and integrations across cloud systems and enterprise data sources
• Implement and continuously improve RAG pipelines for tax artifacts and internal knowledge, including ingestion, retrieval tuning, and evaluation
• Integrate AI workflows with existing internal platforms (e.g., assistant frameworks) and back-end services through robust APIs
• Define and maintain tool/function schemas and orchestration patterns; implement streaming updates, interrupts, and human-in-the-loop steps as needed
• Partner with other engineers to set direction, mentor, and unblock the team – helping establish strong foundations for the AI initiative
• Build in quality from day one: automated tests, evaluation checks, monitoring/telemetry, and performance optimization for network-bound workloads
• Participate in Agile ceremonies (daily scrums, refinement/grooming, planning) and collaborate through peer review, pair programming, and strong documentation
• Apply best practices, design principles, and security standards throughout the SDLC, with a focus on reliability and responsible AI

Requirements:

• 5+ years of professional software development experience (ideally 7+ years across backend/API/integration and cloud platforms)
• Proven ability to ship production-grade LLM applications (RAG, tool/function calling, agent orchestration) with reliability, security, and observability
• Strong ownership mindset and passion for AI engineering – curiosity, experimentation, and a drive to continuously improve the product and the team
• Excellent communication and collaboration skills; ability to guide, mentor, and unblock other engineers as we build out an AI engineering capability
• Strong software engineering background (not a research-only data science profile): designing, building, and operating production systems
• Proficiency in at least one backend language used for AI systems (Python preferred) and comfort integrating with enterprise stacks (C#/.NET is a plus)
• Hands-on experience building and integrating RESTful APIs; GraphQL experience is a plus
• Strong understanding of distributed systems fundamentals: concurrency, async I/O, resiliency/retries, rate limits, caching, and performance optimization
• Experience integrating with external services and internal platforms via APIs and event-driven patterns
• Hands-on experience building LLM-powered applications end-to-end: prompt design, tool/function interfaces, structured outputs, and streaming user experiences
• Experience with RAG systems: document ingestion pipelines, chunking/metadata, embeddings, retrieval strategies, grounding, and evaluation
• Experience with agentic frameworks and orchestration concepts (planning, routing, tool use, human-in-the-loop interruptions)
• Frameworks may include LangGraph, LangChain, Microsoft Semantic Kernel, or equivalent
• Understanding of LLM application quality and safety: evaluation approaches, hallucination mitigation, prompt/version management, and guardrails for sensitive data
• Experience working with model platforms (e.g., Azure OpenAI/OpenAI or similar) and designing for reliability (timeouts, fallbacks, quotas)
• Strong knowledge of Azure cloud services used for enterprise AI solutions (e.g., Functions, Storage, Key Vault, App Configuration, Application Insights)
• Experience with search and retrieval services (Azure AI Search or similar) and building scalable, network-bound workloads
• Ability to design systems with production observability: structured logging, tracing, metrics, and incident-friendly debugging
• Strong background in unit and integration testing; ability to build and maintain AI evaluation harnesses (golden sets, regression tests, automated checks)
• Hands-on experience with CI/CD and automated deployments (Azure DevOps preferred), including containerization (Docker)
• Strong understanding of source code version control with Git/GitHub
• Familiarity with authentication/authorization patterns (JWT/OAuth/OIDC) and secure secret management
• High ownership and a builder mindset: you take ideas from ambiguous problem statements to working solutions
• Passion and curiosity for AI engineering; you actively explore new approaches and share learnings with the team
• Strong written and verbal communication; able to explain complex systems clearly to engineers and non-engineers
• Highly collaborative and effective in distributed teams across time zones; comfortable pairing/mobbing when needed

Nice to have:

• Direct experience with LangGraph and/or LangChain for multi-agent workflows
• Familiarity with emerging agentic ecosystem concepts/protocols (e.g., MCP, A2A, ADK or similar)
• Experience integrating AI services into .NET (ASP.NET Core) applications or building AI microservices that serve enterprise applications
• Experience with event-driven architectures (service bus, event hubs) and real-time updates/streaming to UI
• Experience working with tax/enterprise document corpora and governance constraints (PII, retention, access control)

Offer:

• Private medical care
• Co-financing for the sports card
• Training & learning opportunities
• Constant support of dedicated consultant
• Employee referral program