Associate AI Engineer

Kaleris • Alpharetta, GA

6d

About The Position

As an Associate AI Engineer on the IT AI team, you will work alongside our team of talented engineers to build GenAI agents, optimize LLM prompts, implement RAG pipelines, and integrate AI with our enterprise applications. You will work on Microsoft Azure AI Foundry, Anthropic Claude, contributing to the AVA AI platform that powers AI features across Kaleris. This is a hands-on engineering role, not a support or QA position. You will write production code, instrument token telemetry, design data schemas, and ship features. Equally important — you will engage with business stakeholders to understand their workflows, gather requirements, and help determine whether AI is the right tool for the job. Sometimes the best solution isn't AI at all, and we value engineers who can think that way. A master's-level background in AI/ML, data science, or computer science will help you ramp quickly and contribute meaningfully.

Requirements

• Degree in Computer Science, AI/ML Engineering, Data Science, or related technical field
• Strong Python proficiency — clean, testable, production-quality code
• Foundational knowledge of LLMs, prompt engineering, and GenAI system design through coursework, research, or projects
• Familiarity with REST APIs and ability to write and read API integration code
• Working knowledge of Git and basic CI/CD concepts
• Strong written and verbal communication skills; able to translate technical concepts for non-technical audiences and business context for technical teams
• Proven ability to gather and document requirements from stakeholders with varying levels of technical background
• Comfort facilitating or participating in discovery sessions, asking clarifying questions, and synthesizing what you hear into actionable problem statements
• Collaborative mindset — you work well across teams, share context proactively, and know when to escalate
• Curiosity and eagerness to learn — you actively seek to understand why a business process works the way it does before proposing how to change it
• Adaptability — you're comfortable moving between a coding problem in the morning and a stakeholder conversation in the afternoon
• Problem-first thinking — you resist the urge to default to AI as the answer; you evaluate the problem first and select the right tool for the job
• Ownership — you follow through, communicate blockers early, and take accountability for your deliverables
• Resilience and coachability — you welcome feedback, iterate without defensiveness, and grow from it
• Attention to detail — in both code quality and in capturing what stakeholders actually need, not just what they say they need
• Positive, team-oriented attitude — you contribute to a culture where people help each other succeed

Nice To Haves

• Hands-on experience with Azure, AWS, or GCP AI/ML services
• Experience with LangChain, LlamaIndex, or Semantic Kernel
• Exposure to vector databases (Azure AI Search, Pinecone, Weaviate, Chroma)
• Experience with PostgreSQL and an ORM (Prisma, SQLAlchemy, or equivalent)
• Basic Docker and containerized deployment experience
• Experience in requirements gathering, business analysis, or solution design — even informally (e.g., academic projects, internships, or consulting)
• AI/ML research, hackathon, or open-source project participation
• Familiarity with supply chain, logistics, or enterprise SaaS environments is a plus

Responsibilities

• Build GenAI agents and AI-powered workflows on Azure AI Foundry and with Anthropic Claude APIs under senior engineer guidance
• Write, test, and optimize prompts for LLMs — including system prompts, few-shot examples, and tool-calling specifications — with a focus on token efficiency and output quality
• Instrument AI calls with token usage logging; contribute to per-user and per-workflow token telemetry dashboards in Azure Monitor
• Implement RAG pipeline components: document ingestion, embedding generation, vector store upsert (Azure AI Search), and retrieval quality evaluation
• Build and maintain AI-native PostgreSQL schemas using Prisma ORM: prompt history, token audit logs, embedding metadata, and evaluation records
• Write integration code connecting AI workflows to Salesforce, NetSuite, and Workday via REST APIs
• Package and deploy AI microservices using Docker; contribute to GitHub Actions CI/CD pipelines
• Follow secure development practices: secret management with 1Password, PII handling in prompts and outputs, prompt injection awareness
• Write technical documentation for prompt patterns, integration designs, and AI feature implementations
• Partner with business stakeholders across the organization to understand current workflows, gather requirements, and identify where technology can add meaningful value
• Analyze business problems with an open mind — propose AI-powered solutions where appropriate, but recognize and recommend conventional engineering, process improvements, or configuration changes when those are the better fit
• Translate business needs into clear technical requirements and work with cross-functional technical teams (infrastructure, enterprise apps, data) to design and implement solutions
• Participate in discovery conversations and requirements sessions, asking the right questions to surface root causes, not just symptoms
• Develop a working knowledge of Kaleris business processes — supply chain execution, terminal operations, logistics workflows — to become a more effective solution partner over time

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level