
Job Description
Ovii's Interpretation of the Role
We need a hands‑on AI Engineer to build and ship LLM‑driven agent harnesses on our internal platform. You’ll design tools, evaluation pipelines, and guardrails while collaborating with data engineers. The role is fully remote and part of the Business Intelligence Innovation team.
Role Snapshot
- AI Engineer
- Python backend development
- LLM production
- Agent platform engineering
- Remote full‑time
- Business Intelligence team
Must-Have Requirements
- Python (3+ years professional)
- LLM production experience (1+ years)
- LangChain or LangGraph knowledge
- LLM observability tools (CloudWatch, LangSmith, MLflow, OpenTelemetry)
- Evaluation framework design (MLflow, DeepEval, LLM‑as‑judge)
- Git
- Docker
- Modern API frameworks
- Python production services
- LLM production and tool‑calling
Nice-to-Have Signals
- Amazon Bedrock / AgentCore
- Snowflake / Snowpark / Snowflake Cortex
- SQL
- Multi‑agent patterns (supervisor/router, sub‑agent handoff, human‑in‑the‑loop)
- Loyalty, MarTech or AdTech domain experience
- Snowflake data platform
- Loyalty / MarTech / AdTech domain
- Loyalty
- MarTech
- AdTech
Work Setup
- Location: St. Petersburg, USA
- Work mode: REMOTE
- Remote scope: UNSPECIFIED
- Employment type: Full-Time
Not Specified in JD
- Salary range
- Visa sponsorship
- Remote eligibility details
- Equity
- Bonus
What You'll Likely Work On
- Build Python‑based agent harnesses with LangChain/LangGraph, handling tool‑calling, streaming, memory and structured outputs
- Package harnesses for the AgentCore runtime, integrating context, tools, skills and sub‑agents
- Create API integrations and Snowflake‑backed SQL queries that agents invoke
- Design and implement evaluation harnesses, regression suites and LLM‑as‑judge pipelines
- Add guardrails for auth, input/output validation, PII, prompt‑injection and hallucination mitigation
- Own the end‑to‑end lifecycle: prototype, deploy, monitor traces and resolve production issues
- Partner with data engineers on Snowflake retrieval patterns
- Help evolve internal engineering patterns as the stack matures
Good Fit If You Have
- Enjoy building production‑ready AI systems and shipping features quickly
- Comfort with rapid prototyping, iteration and debugging in a remote setting
- Strong written communication and good judgment about release readiness
- Self‑directed learner who can pick up new tools with minimal hand‑holding
- Experience in loyalty, MarTech or AdTech domains is a plus
Skills
- Python
- LangChain / LangGraph
- Amazon AgentCore
- Snowflake & SQL
- Git & Docker
- LLM observability (CloudWatch, LangSmith, MLflow)
- Evaluation frameworks (MLflow, DeepEval)