Sr. AI Engineer (ATL or MSP) job in Atlanta

• AGENTIC APPLICATION DEVELOPMENT: Designs and builds production-grade AI agents and services using strong Python (typing, packaging, async/concurrency) with high-quality unit, integration and contract tests.
• CI/CD & QUALITY REGRESSION: Leads build/test/release automation including automated evaluation gates, container builds, artifact versioning, environment promotion and safe rollout practices to keep main deployable.
• LLM INTEGRATION: Implements multi-model routing, fallbacks and cost/latency trade-offs through the LLM gateway, ensuring deterministic behaviors where possible.
• RETRIEVAL & RAG ARCHITECTURE: Designs retrieval strategies (chunking, embedding strategy, metadata filtering) leveraging vectors to support scalable, multi-tenant use cases.
• OBSERVABILITY & OPERATIONS: Applies telemetry-first practices (logs/metrics/traces), leads trace-first debugging and supports on-call readiness with clear runbooks and postmortems aligned to Operational Excellence.
• PLATFORM COLLABORATION: Designs API/interface contracts, semantic versioning and contribution frameworks to enable multiple teams to build safely on the shared AI platform.
• SECURITY & RESPONSIBLE AI: Incorporates secure-by-default practices including secrets management, least privilege access, safe logging and protections against prompt injection, tool abuse and data leakage.

• Minimum requirement of 4 years of relevant work experience. Typically reflects 5 years or more of relevant experience.

Preferred Experience:

• Experience integrating LangSmith evaluation into CI and production monitoring.
• Familiarity with MCP tool interface patterns and building reusable, secure tool wrappers.
• Experience implementing semantic caching and performance optimization techniques for AI workloads.
• Exposure to AWS infrastructure patterns including IAM, KMS, private networking and secure service-to-service communication.
• Experience governing shared repositories.

The expected salary for this position is $105,000- $178,000. Compensation varies depending on a wide array of factors including but not limited to the specific location, certifications, education, and level of experience. The disclosed range estimate may be adjusted for any applicable geographic differential associated with the location at which the position may be filled. This position is eligible for a discretionary incentive award. The incentive award amount is dependent upon company performance and your personal performance. At Cargill we put people first. As part of your overall rewards, we offer a comprehensive benefit program including medical and/or other benefits dependent on the position offered and hours worked. Visit: https://www.cargill.com/page/my-health/mh-health-and-wellness to learn more (subject to certain collective bargaining agreements for Union positions).

Cargill is committed to providing food and agricultural solutions to nourish the world in a safe, responsible, and sustainable way. Sitting at the heart of the supply chain, we partner with farmers and customers to source, make and deliver products that are vital for living. Our 155,000 team members innovate with purpose, providing customers with life's essentials so businesses can grow, communities prosper, and consumers live well. With over 160 years of experience as a family company, we look ahead while remaining true to our values. We put people first. We reach higher. We do the right thing-today and for generations to come., * Come build the AI platform that engineers across Cargill will use every day-shipping low-code and pro-code AI agents that turn real problems into real outcomes. At Cargill, you're not optimizing vanity metrics; you're helping a global company that puts food on tables around the world deliver better, faster, safer decisions at massive scale. We're looking for engineers with integrity (do the right thing when no one's watching), hunger to learn (stay curious, test, iterate), and a builder mindset (prototype, harden, scale). You'll do well here if you move work forward even with dependencies, communicate clearly, and ship value in increments-building strong relationships while finding practical paths around blockers.