AI Developer

Responsibilities: Develop end-to-end AI solutions including LLM-powered applications, predictive ML models, multi-agent workflows, RAG pipelines, and specialized AI microservices. Implement reusable AI components, libraries, and APIs that streamline application development and accelerate delivery across programs. Integrate AI models with enterprise systems, APIs, data platforms, vector databases, and cloud-native services to deliver scalable mission capabilities. Drive iterative experimentation, prototyping, and model improvement cycles in collaboration with Data Scientists and AI Evaluation Scientists. Design and implement advanced prompt strategies, context management layers, retrieval systems, and LLM orchestration logic. Build scalable inference services, optimize model performance, and collaborate with LLMOps to enable robust deployment, monitoring, and continuous improvement. Translate user needs and mission workflows into intuitive, reliable AI-powered features through active partnership with designers and product teams. Implement secure-by-design and trustworthy AI practices, including safety guardrails, input sanitization, content filtering, and integration of evaluation metrics. Contribute to internal AI frameworks, code patterns, and shared accelerators that raise delivery quality across the AI & Data Exploitation Practice. Mentor junior developers, conduct code reviews, and support engineering excellence across multi-disciplinary AI delivery teams. Stay current with emerging AI techniques, libraries, foundation models, and agent frameworks, evaluating their applicability to client missions. You will contribute to the growth of our AI & Data Exploitation Practice!

Qualifications: Ability to hold a position of public trust with the U.S. government. Bachelor's degree and 5 years of relevant experience; OR Master's degree and 3 year of relevant experience; OR No degree and 9 years of relevant experience. Proficiency in Python; comfortable working across the AI/ML tooling ecosystem Solid understanding of RAG architectures - chunking strategies, embedding models, vector stores, retrieval evaluation Experience with at least one LLM orchestration framework (LangChain, LlamaIndex, LangGraph, CrewAI, or equivalent) Strong prompt engineering skills - system prompts, few-shot design, chain-of-thought, and iterative refinement Experience containerizing and deploying applications with Docker Proficiency with Git and collaborative version control workflows Ability to read and write REST APIs; comfortable integrating third-party services and models Strong communication skills - you will interact with clients and translate fuzzy requirements into working systems Ability to hold a position of public trust with the U.S. government. Preferred Experience with cloud-native AI services, particularly AWS Bedrock for managed LLM inference Familiarity with serverless compute (AWS Lambda) and managed ETL pipelines (AWS Glue) for data ingestion workflows Working knowledge of vector and relational data stores including AWS RDS Postgres (pgvector) and OpenSearch Container orchestration experience with Kubernetes for deploying and scaling AI services CI/CD pipeline experience with Jenkins or similar build orchestration tools Observability and logging experience for LLM pipelines - LangSmith, Arize, or equivalent Familiarity with LLM evaluation frameworks such as RAGAS or DeepEval for measuring RAG and model quality Hands-on experience with workflow automation platforms - n8n, Prefect, Airflow, or similar Experience with MCP and tool-serving infrastructure (MCPO or similar) Experience designing multi-agent systems with agent-to-agent coordination patterns Experience with graph databases (Neo4j, Memgraph) and Graph RAG approaches Prior consulting, agency, or client-delivery experience