Two Positions: Senior Agentic AI Engineer(Healthcare)- Remote - Contract

Job Title: Senior Agentic AI Engineer(Healthcare)

Number of Openings: 2

Location: Remote

Contract: 3+Months(Possibility of Extension)
Experience: 6+ Years
Role Type: Senior Engineering / Hands-on Development

Skills Needed: LangGraph / Stateful Orchestration, Amazon EKS / Kubernetes, Amazon Bedrock, Databricks / Unity Catalog, State and Memory Services, APIs / MCP Tools, Observability and Evaluation, AI Security and Governance

Role Specializations

Position 1 – Agent Orchestration and Runtime

• LangGraph supervisor workflows and module routing.
• Stateful orchestration, checkpointing, retries, and recovery.
• Parallel execution, streaming, and human approvals.
• AWS EKS deployment, scaling, and runtime observability.

Position 2 – Context Engineering, Tools, and Data Intelligence

• Semantic contracts and metadata/context resolution.
• Dynamic table and column selection.
• Governed Text-to-SQL and Databricks integrations.
• SQL validation, evidence retrieval, and AI evaluation datasets.

Job Summary

We are seeking two experienced Senior Agentic AI Engineers to design, develop, deploy, and maintain production-ready agentic AI solutions. The ideal candidates will have strong hands-on experience with Python, LangGraph, Amazon Bedrock, AWS EKS, and Databricks.

The engineers will build scalable AI agent workflows, integrate enterprise tools and APIs, implement context engineering and governed data access, and ensure the reliability, security, and performance of AI applications in production environments.

Key Responsibilities

• Design and develop agentic AI workflows using Python and LangGraph, including supervisor routing, reusable subgraphs, parallel execution, and persistent state management.
• Integrate Amazon Bedrock foundation models, guardrails, streaming, structured outputs, model fallbacks, and token/cost controls.
• Develop and secure REST APIs, OpenAPI services, and MCP-based tools for enterprise integrations.
• Deploy and manage AI applications on AWS EKS using Docker, Kubernetes, Helm, and container orchestration practices.
• Implement durable workflow checkpoints using PostgreSQL/RDS and transient caching and coordination using Redis.
• Integrate Databricks SQL, Unity Catalog, Delta Lake, and metadata services for secure, governed data access.
• Build context-engineering capabilities, including metadata retrieval, semantic contracts, relevant table selection, and logical-to-physical data mappings.
• Develop automated AI evaluation frameworks, regression tests, and quality gates to measure accuracy, groundedness, and reliability.
• Implement observability using OpenTelemetry, Arize Phoenix, or equivalent tools to monitor latency, errors, retries, model usage, and costs.
• Apply AI security and governance controls, including prompt-injection protection, least-privilege access, PHI/PII protection, and auditability.
• Troubleshoot production issues and continuously improve the reliability, performance, scalability, and cost-effectiveness of AI solutions.

Required Technical Skills

• Programming: Advanced Python, asynchronous programming, FastAPI, Pydantic, and typed schemas.
• Agentic AI: Hands-on LangGraph experience, stateful workflows, conditional routing, retries, persistent checkpoints, and human-in-the-loop approvals.
• AWS: Amazon Bedrock, EKS, Kubernetes, Docker, Helm, and production deployment practices.
• Databases and State Management: PostgreSQL/RDS, Redis, transactions, durable checkpoints, caching, and recovery.
• API and Tool Integration: REST, OpenAPI, MCP, authentication, authorization, versioned schemas, and secure tool execution.
• Data Engineering: Databricks SQL, Databricks SDK/APIs, Unity Catalog, Delta Lake, and governed SQL execution.
• Context Engineering: Semantic data contracts, metadata retrieval, business metrics, dimensions, relationships, approved joins, and dynamic table/column selection.
• AI Evaluation and Monitoring: DeepEval or equivalent evaluation frameworks, OpenTelemetry, Arize Phoenix, and automated regression testing.
• Security: Prompt-injection defense, least-privilege access, tenant isolation, sensitive-data protection, and secure logging.

Experience Requirements

• 6+ years of professional experience in software, data, cloud, or platform engineering.
• At least 2 years of hands-on LLM/agentic AI engineering experience.
• Experience delivering at least one production or production-pilot agentic AI solution.
• Demonstrated ownership of development, testing, deployment, troubleshooting, and production support.
• Strong communication and collaboration skills when working with architects, data engineers, security teams, and business stakeholders.

Preferred Qualifications

• Experience in healthcare, Medicaid, claims, or other regulated-data environments.
• Experience integrating multiple data platforms or model providers.
• Knowledge of data quality, data lineage, AI FinOps, and production incident management.
• Experience with portable semantic-contract approaches such as Apache Ossie or equivalent.