Senior AI/ML Engineer

DeWinter Group; Durham (NC); Remote; USD 150,000 - 210,000; Full time

Job summary

DeWinter Group is seeking a Senior AI/ML Engineer to lead the design of multi-agent orchestration workflows and scalable AI platforms in a fully remote setting. The role focuses on building reliable enterprise-grade systems with prompt templating, intent routing, and conversation memory using Python and FastAPI.

You will evaluate LLMs, implement gating and entitlement routing for secure multi-tenant environments, and develop observability with Datadog, OpenTelemetry, and Snowflake.

Qualifications

• 5+ years of software engineering experience with Python, including high-throughput, asynchronous service development.
• 2+ years building production-class LLM applications, with agent workflows and multi-agent protocols such as LangChain or LlamaIndex.
• Deep understanding of MCP, RESTful API design, and orchestration architectures.

Responsibilities

• Design, develop, and optimize multi-agent orchestration workflows, including prompt templating and conversation memory.
• Integrate and standardize MCP servers and tools across enterprise products.
• Build automated evaluation pipelines to benchmark LLM accuracy, routing, and latency.

Skills

Python async

LLM apps

MCP / REST

Evaluation pipelines

AWS services

Observability

LangChain / LlamaIndex

Education

Bachelor’s or Master’s in CS/Engineering

Tools

LangChain

LlamaIndex

FastAPI

Datadog

OpenTelemetry

Snowflake

Job description

Join Our Team as a Senior AI/ML Engineer

Are you passionate about pioneering advanced AI and machine learning solutions that drive innovation? We are seeking a highly skilled Senior AI/ML Engineer to lead the development of cutting-edge agent orchestration systems and transformative workflows. This role plays a vital part in building scalable, reliable AI platforms that empower enterprise-level applications in a fully remote setting.

Key Responsibilities:

• Design, develop, and optimize multi-agent orchestration workflows, including prompt templating, intent routing, and conversation memory, using Python, asyncio, and FastAPI.
• Integrate and standardize Model Context Protocol (MCP) servers and tools across various enterprise products.
• Build automated evaluation pipelines to benchmark LLM accuracy, routing, and latency, ensuring high standards in performance and compliance.
• Implement dynamic gating and entitlement routing to support secure, multi-tenant environments.
• Develop telemetry, monitoring, and logging solutions for system observability using Datadog, Snowflake, and OpenTelemetry.

Required Skills:

• 5+ years of software engineering experience with Python, including high-throughput, asynchronous service development.
• 2+ years building production-class LLM applications, with expertise in agent workflows, function calling, and multi-agent protocols such as LangChain or LlamaIndex.
• Deep understanding of Model Context Protocol (MCP), RESTful API design, and orchestration architectures.
• Proven experience designing automated evaluation and benchmarking strategies for LLMs.
• Familiarity with AWS cloud services (ECS/EKS, Lambda, SQS/Kafka), vector databases, and data warehouses like Snowflake.
• Strong commitment to software craftsmanship, testing, automation, and team collaboration.

Nice to Have Skills:

• Prior experience in enterprise SaaS or tax/compliance technology domains.
• Knowledge of streaming architectures, semantic caching, and latency optimization.
• Understanding of IAM/RBAC models and enterprise security standards such as SOC 2, ISO.

Preferred Education & Experience:

• Bachelor’s or Master’s degree in Computer Science, Engineering, or related field.
• Proven track record in leading complex AI/ML projects and working within fast-paced tech environments.

Additional Requirements:

• This position is fully remote with no travel requirements.
• Availability to start around November 30th for a 1-year engagement.
• W2 employment status only; no monetary details provided here.

Elevate your career by contributing to innovative AI platforms that shape the future of enterprise intelligence.