AI/ML Engineer

Kforce has a client in Maryland Heights, MO that is seeking an AI/ML Engineer.Job Responsibilities: Observability: Assess CloudWatch, X-Ray, Bedrock logging, AgentCore traces vs. agentic workflow requirements; Produce gap analysis Setup observability in Dynatrace Design post-deployment validation pipeline for agents & MCP servers (deployment health + tool registration checks) Implement distributed tracing & structured logging: LLM decisions, tool selections, sub-agent calls, MCP interactions Evaluate LangFuse/LiteLLM proxy vs. AWS-native; Deliver target-state observability architecture recommendation Cost Tracking & TCO: Extend tagging taxonomy to cover agent runtimes, MCP servers, vector DBs, Bedrock token consumption per namespace Design cost visibility model: aggregate agent, MCP, vector DB, and Bedrock token costs per team/department Build CloudWatch (or equivalent) dashboards for per-team spend; Configure AWS Budgets with alerting thresholds Automate cost reports delivered via email Connectivity issues: Integrate alert notifications to Microsoft Teams channels and email; Route by resource ownership tags Author runbooks linked to every alert; Publish in Confluence for developer self-service resolution Evaluate AWS-native vs. third-party monitoring stack; Deliver recommendation aligned to observability architecture Security & Access Control: Assess current IAM + tagging approach for multi-team isolation; Identify scalability gaps and risks Evaluate Cedar policy engine (AgentCore) for fine-grained tool access control 3 years of experience in AI/ML & Cloud Deep proficiency in AWS (IAM, CloudWatch, Bedrock, Lambda); Along with data warehouse (DWH) knowledge and building models on top of existing data platforms Familiarity with the LLM lifecycle, including prompt execution, token usage, and frameworks like LangChain or AgentCore Advanced experience with Terraform and CI/CD pipeline design Experience working in an Agile environment with integrated tools like Microsoft Teams and Confluence Strong programming background; Bedrock and AgentCore are technologies they are evaluating Experience building systems utilizing: RAG LLMs AWS AI/ML Skills: Some level of AI expertise required Experience building agents Ability to write MCPs Experience orchestrating interactions between agents Experience with: Building on top of and calling LLM APIs Graph databases: Neptune; Neo4j SageMaker or similar platforms Python or Java Databricks or Data Lake solutions Kafka and Spark are present, but the team already has support in those areas The pay range is the lowest to highest compensation we reasonably in good faith believe we would pay at posting for this role. We may ultimately pay more or less than this range. Employee pay is based on factors like relevant education, qualifications, certifications, experience, skills, seniority, location, performance, union contract and business needs. This range may be modified in the future. We offer comprehensive benefits including medical/dental/vision insurance, HSA, FSA, 401(k), and life, disability & ADD insurance to eligible employees. Salaried personnel receive paid time off. Hourly employees are not eligible for paid time off unless required by law. Hourly employees on a Service Contract Act project are eligible for paid sick leave. Note: Pay is not considered compensation until it is earned, vested and determinable. The amount and availability of any compensation remains in Kforce's sole discretion unless and until paid and may be modified in its discretion consistent with the law. This job is not eligible for bonuses, incentives or commissions. Kforce is an Equal Opportunity/Affirmative Action Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, pregnancy, sexual orientation, gender identity, national origin, age, protected veteran status, or disability status. By clicking "Apply Today" you agree to receive calls, AI-generated calls, text messages or emails from Kforce and its affiliates, and service providers. Note that if you choose to communicate with Kforce via text messaging the frequency may vary, and message and data rates may apply. Carriers are not liable for delayed or undelivered messages. You will always have the right to cease communicating via text by using key words such as STOP. Kforce