Senior Software AI Engineer

About This Opportunity

We are representing a confidential AI software organization serving defense, public sector, and regulated enterprise clients. Our talent team is seeking a Senior Software AI Engineer to build production agentic systems, data pipelines, and LLM operations infrastructure that power real-world AI capabilities.

This is a hands-on execution role. You'll ship code weekly, operationalize agent workflows using industry-leading SDKs and standards, build evaluation and observability layers for LLM quality, and create robust ingestion pipelines that transform diverse data sources into queryable knowledge bases. This work supports AI-driven matching, analysis, and intelligence systems in SOC 2 and NIST-compliant environments.

Responsibilities

• Design, build, and operate production agentic workflows using agent SDKs, MCP servers, and Agent Skills standards
• Develop and maintain LLM evaluation and observability infrastructure with golden datasets, LLM-as-judge patterns, and cost/latency tracking
• Engineer data pipelines for document ingestion, structured data processing, and external source integration with quality validation and deduplication
• Own retrieval quality through hybrid search combining vector, keyword, and metadata retrieval with continuous improvement via reranking and query expansion
• Build custom MCP tools and Agent Skills to accelerate engineering team productivity
• Collaborate with full-stack engineers on AI integration points and contribute to incident response for AI services
• Leverage agentic coding tools to ship faster while maintaining production quality

What We're Looking For

Required:

• 7+ years professional software engineering experience with 3+ years focused on AI/ML or data engineering
• Production experience building and operating LLM applications (agents, tool-use, or orchestrated workflows) using APIs from major providers
• Strong data engineering background building robust, scalable pipelines for AI/ML workloads
• Hands-on LLM operations experience implementing evals and observability for production systems
• Production retrieval experience with vector databases and/or search engines (OpenSearch, Elasticsearch)
• Modern Python proficiency: FastAPI, Pydantic, async/await, modern dependency management
• Demonstrated ability using Claude Code, Codex, or similar agentic coding tools
• Experience with Docker, Kubernetes, and AWS
• US citizenship required (DoD contracting and FedRAMP compliance requirements)

Preferred:

• Deep experience with Agent Skills standards, custom MCP servers, and agent SDKs across major vendors
• Advanced RAG expertise including GraphRAG, agentic RAG, contextual retrieval, and reranking strategies
• Graph data experience with knowledge graphs, graph databases, or graph-based retrieval
• Model selection and rightsizing across quality, cost, and latency tradeoffs
• Streaming data experience with Kafka or Kinesis for real-time knowledge base updates
• Research background, open-source contributions, or advanced degree in ML/IR/NLP

Technology environment: Python primary; multi-provider LLM SDKs; agent frameworks and MCP servers; Langfuse for evals; vector databases; PostgreSQL; Amazon S3; Kubernetes on AWS EKS; DataDog and OpenTelemetry

How We Work With You

Candidates apply directly through Get A Job.ai. Our recruiting team will conduct an initial screen to understand your background and align expectations. We then submit qualified candidates to our client for their evaluation process. Please do not contact the client directly—we coordinate all communication to ensure the best experience for everyone involved.

Pay

Pay details will be discussed during the screening process based on experience and qualifications.

Equal Opportunity: Get A Job.ai is committed to inclusive hiring practices. We encourage applications from candidates of all backgrounds and experiences.