> Markdown version of [/jobs/ext/3849874-staff-machine-learning-engineer-agentic-ai](https://www.wearedevelopers.com/jobs/ext/3849874-staff-machine-learning-engineer-agentic-ai). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Staff Machine Learning Engineer - Agentic AI - **Company:** ELLKAY, LLC. - **Location:** United States (Remote available) - **Experience:** Experienced - **Salary:** $170,000.0 - $190,000.0 - **Contract:** Permanent contract - **Skills:** LangGraph Framework, A/B Testing, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Amazon S3, Cloud Engineering, Data Normalization, Amazon DynamoDB, Statistical Hypothesis Testing, Identity and Access Management, Information Retrieval, JSON, Python (Programming Language), Key Management, PostgreSQL, Machine Learning, Open Web Application Security, Search Technologies, Service Discovery, Software Engineering, TypeScript, Management of Software Versions, AWS Cdk, Data Logging, Evaluation Pipelines, Fast Healthcare Interoperability Resources, Retrieval-Augmented Generation, Large Language Models, Multi-Agent Systems, Prompt Engineering, HNSW (Hierarchical Navigable Small World), Model Validation, Boto3, Llamaindex, Indexer, Backend, Agentic-AI, Fastapi, Pandas, Amazon Bedrock, Structured Output Generation, CrewAI, Health Level Seven International, AWS Fargate, AutoGen, Machine Learning Operations, Claude, Cloudwatch, Api Gateway, Amazon Simple Queue Service (SQS), GPT, Dynatrace, Serverless Computing, K Means, OpenSearch, Microservices - **Published:** October 21, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=84b6b755fd9012e4 ## About the Role Technical Skills * Python Stack: Proficiency with Pydantic v2, Pandas/Polars, FastAPI, Boto3, Asyncio, and Agent/LLM frameworks (e.g., LangGraph, AutoGen, LlamaIndex). * Agentic AI & Foundation Models: Proven experience designing stateful agents, function/tool calling interfaces, autonomous reasoning loops, structured output generation, and evaluation harnesses. * AWS Services: Production experience with Lambda, API Gateway, Step Functions, EventBridge, SQS, SNS, ECS Fargate, Aurora PostgreSQL, DynamoDB, S3, and AWS CDK. * Vector Search & Memory: Practical knowledge of OpenSearch Serverless, k-NN algorithms, hybrid retrieval, and ranking optimization for RAG and agent memory stores. * Machine Learning: Experience with scikit-learn, clustering algorithms, and confidence calibration techniques. * Healthcare Standards (preferred): Working knowledge of FHIR R4, HL7 v2, USCDI, LOINC, SNOMED, and RxNorm. * Security: Good understanding of IAM, KMS, secrets management, and OWASP security principles. Experience * 10+ years of software engineering experience with at least 3 years focused on production AI/ML and GenAI/Agentic systems. * Proven track record of deploying production ML and agentic applications at scale. * Experience with healthcare data or regulated industries strongly preferred. * Demonstrated ability to design and implement end-to-end ML and agent evaluation frameworks. * Well versed in AI development leveraging tools such as Codex/Claude Code ## Description We're looking for a versatile Full Stack AI/ML Engineer who can architect, build, and deploy production-grade AI/ML and Agentic AI systems on AWS infrastructure. This role combines deep expertise in foundation models, agentic frameworks, healthcare data standards, and serverless cloud architecture to create scalable, secure, and compliant AI solutions for healthcare organizations., AI/ML & Agentic Engineering * Agentic Frameworks & Architectures: Architect, implement, and deploy end-to-end Agentic AI systems utilizing tool calling, stateful multi-agent collaboration, dynamic task routing, reflection loops, and self-correction workflows using frameworks like LangGraph, AutoGen, CrewAI, or Bedrock Agents. * Prompt & Tool Engineering: Design and implement production foundation model applications using advanced prompt engineering, structured output design, function-calling patterns, dynamic tool retrieval, and hallucination mitigation strategies. * Memory & Vector Search: Build and optimize vector search and long-term memory solutions using OpenSearch Serverless with k-NN, including HNSW/IVF parameter tuning, hybrid retrieval (lexical + semantic), and multi-stage ranking pipelines (BM25 + dense + re-ranking) for RAG and agent context retrieval. * Bedrock & Guardrails: Develop and deploy Amazon Bedrock and Bedrock Agent solutions leveraging Claude family models, Titan Embeddings v2, and Guardrails for PHI/PII detection while optimizing for provisioned vs. on-demand throughput. * Classical ML: Implement classical ML pipelines including clustering algorithms (HDBSCAN, k-means), confidence score calibration (Platt scaling, isotonic regression), and model evaluation frameworks. Healthcare Data & Standards * Design and implement systems that work with FHIR R4 resources, HL7 v2 message structures, and USCDI data elements. * Build ontology retrieval and agent tool interfaces against LOINC, SNOMED, and RxNorm terminologies to support clinical decision-making and data normalization. * Ensure HIPAA compliance and implement appropriate security controls for protected health information (PHI) across LLM inputs, tool payloads, and agent memory states. Backend & Infrastructure * Build high-performance APIs and agent execution backends using FastAPI and Pydantic v2 with async I/O patterns, robust retry/backoff mechanisms, state management, and structured error handling. * Design and deploy AWS serverless architectures including Lambda (Python + container), API Gateway (REST + HTTP), Step Functions, EventBridge, SQS, and SNS. * Implement container-based workloads for agent microservices on ECS Fargate with auto-scaling policies, service discovery, and Fargate Spot optimization. * Architect data and state solutions using Aurora PostgreSQL Serverless v2, DynamoDB, and S3 with appropriate indexing, partitioning, caching, and lifecycle policies. * Write production-grade Infrastructure as Code using AWS CDK (TypeScript or Python) supporting multi-tenant provisioning and cross-account deployments. Observability & Security * Implement comprehensive observability using AWS X-Ray distributed tracing, CloudWatch metrics/logs/alarms, agent execution trajectory tracing, structured JSON logging, and correlation ID propagation. * Apply security engineering best practices including IAM least-privilege roles for tool executions, KMS envelope encryption, Secrets Manager rotation, JWT validation, tenant isolation via session tags, and OWASP API Top-10 awareness. Evaluation & Quality * Design rigorous evaluation frameworks for foundation models and AI agents, including tool selection precision, execution success rates, benchmark creation, per-class metrics, held-out test sets, label leakage prevention, and statistical significance testing. * Implement prompt and agent strategy versioning, human-in-the-loop evaluation pipelines, and A/B testing frameworks to continuously improve performance.