Senior AI Engineer

Contract/Contract-To-Hire/Remote (W-2 & No Visa Sponsorship or Transfer Available)

We’re looking for a Senior ML Engineer with strong hands-on experience in GenAI agent development and modern AI engineering. This role focuses on building production-grade agents, MCP integrations, and enterprise knowledge systems using our cloud and data stack.

Key Skills

• Experience building and deploying GenAI agents (including open-source LLM agents) in production environments.

• Strong knowledge of MCP, tool integrations, and agent orchestration.

• Ability to design and maintain knowledge bases, vector search, and retrieval systems.

• Cloud expertise in Azure (preferred) or AWS.

• Strong SQL skills and experience with Snowflake.

• Experience working with Databricks for data and ML workflows.

• Solid background in traditional ML (classification, clustering, etc.).

• Ability to build evals, guardrails, and safety layers for agents at scale.

• Experience with MLOps and LLM Observability.

• Experience building CI/CD pipelines (Github, DevOps).

What This Person Will Do

• Design, build, and maintain production‑grade APIs, microservices, and internal SDKs that support AI models, LLM agents, retrieval pipelines, and tool integrations.

• Develop and refine GenAI and agentic systems, including MCP tools, secure system integrations, and scalable agent‑orchestration infrastructure.

• Create and maintain knowledge bases, retrieval pipelines, and vector search systems to power RAG and agent workflows across internal platforms.

• Implement comprehensive observability for LLM agents, retrieval pipelines, and AI microservices, covering monitoring, logging, tracing, drift detection, hallucination tracking, latency, cost, and quality metrics.

• Build automated evaluation and regression‑testing pipelines for agents, prompts, tools, and model updates to ensure reliability and continuous improvement.

• Develop frameworks for prompt versioning, experiment tracking, reproducibility, and model governance, ensuring consistent and auditable AI development practices.

• Establish and maintain MLOps and LLMOps pipelines, including model training, deployment, CI/CD and environment promotion (dev → QA → prod)

• Optimize model serving and inference infrastructure for performance and cost efficiency (batching, caching, quantization, GPU/CPU autoscaling).

• Collaborate with data scientists and cloud teams to productionize models, ensure reproducibility, and support scalable AI systems.

• Work across Azure, Snowflake, and Databricks to support production AI systems, data pipelines, and model deployments.