Senior AI Agent Engineer / AI Systems Engineer

Hello Professionals,Cogent Data Solutions LLC is hiring a Senior AI Agent Engineer / AI Systems Engineer for a contract role supporting an enterprise IT engagement in Annapolis, MD. This position is part of a project awarded through an existing IT services agreement with our client.Note: This opportunity is offered solely through Cogent Data Solutions LLC, a consulting firm supporting multiple public sector IT initiatives. The end client is a government entity; however, this is not a direct hire or employment opportunity with any government agency.Job Title: Senior AI Agent Engineer / AI Systems EngineerExperience: 3 yearsClient Name: Public-Sector CustomerJob Location: - (Hybrid - Annapolis, MD )Bachelor of Science in Engineering, Computer Science, Data Science, or Mathematics, or arelated field (as determined by the AOC).1.System Design & Collaboration:Work within established constraints regarding infrastructure, programming languages, andmodel selectionContribute to technical decision-making related to data processing, retrieval strategies, andsystem integrationCollaborate with team members to define agent architectures, workflows, and system designdecisionsEvaluate and select appropriate approaches for given tasks, including determining when touse LLM-based versus non-LLM techniquesDesigning and building software systems that integrate AI/ML techniques to automate tasks,assist internal users, and improve user-facing services.2. Testing, Evaluation, and Quality Assurance:Assist in the design and implementation of testing and evaluation pipelines for AI/MLsystemsDevelop unit and integration tests for AI-enabled workflows and data pipelinesGenerate and utilize synthetic data to support evaluation and benchmarking effortsContribute to improving system performance, including accuracy, latency, and costefficiency3. Deployment & Operations:Support deployment of AI/ML applications within a hybrid cloud environmentWork with containerized applications to ensure reliable deployment and updates.Optimize systems for environments with limited computational resources, including minimalGPU availability4. General Responsibilities:Deliver production-grade systems aligned with defined requirements, while supportingiterative improvement of evolving toolsDocument system designs, workflows, and technical decisions as requiredStay informed on relevant advancements in AI/ML and apply them where appropriate withinproject constraintsExperience with:(1) SQL and relational database systems (e.g., PostgreSQL)(2) Fine-tuning small language models or embedding models(3) Contributing to or maintaining open-source software projects(4) Graph databases or graph extensions (e.g., Neo4j, Apache AGE)(5) Designing and implementing multi-agent or task-oriented AI systems(6) Embedding models, vector similarity, re-ranking, and graph retrieval techniques inRAG systems(7) Version control systems (e.g., Git), containerization technologies (e.g., Docker), andservice-oriented architectures(8) Collaborating with large language models (LLMs), including both API-basedintegration and local deployment(9) Validating AI-generated outputs, mitigating hallucinations, and integrating AI toolsinto production service pipelinesb. Ability to:(1) Understand data structures, algorithms, and clean coding principles(2) Select and apply appropriate techniques (LLM and non-LLM) based on taskrequirements(3) Develop and improve testing and evaluation pipelines for AI systems, including useof synthetic data(4) Demonstrate proficiency in Python, including the ability to develop production-grade backend services, APIs, middleware, and data pipelines.(5) Design and implement AI/ML systems that operate effectively on complex,inconsistent, or evolving datasets while balancing accuracy, latency, and cost (tokenconsumption)(6) Collaborate with team members to define system architecture, agent workflows, anddata pipelines while working in constrained environments, including limited GPUavailability and predefined infrastructurec. Knowledge of:(1) Hybrid cloud environments and distributed system considerations(2) Threading, asynchronous processing, and queues in backend servers(3) React and Microsoft Teams Toolkit for developing chatbot user interfaces(4) Non-llm data analysis techniques for structured, semi-structured, and unstructureddata(5) Classical natural language processing (NLP) techniques in addition to LLM-basedapproaches(6) Data science and LLM-related libraries in Rust or other performance-orientedprogramming languages