AI/ML Engineer

1.       AI-ML Engineer (Senior)

Duration: 12 Months +

Remote

Key Responsibilities

·       Design, implement, test, and deploy agentic AI systems and multi-agent workflows to solve complex customer problems

·       Lead technical discussions, drive architecture decisions, and mentor the technical team

·       Architect and integrate agent orchestration frameworks with tool/API ecosystem

·       Own and deliver major solution areas end-to-end with minimal oversight

Must Have

·       5-7+ years building production-grade ML or GenAI systems; advanced Python

·       Hands-on experience with agentic frameworks (Strands, LangGraph, CrewAI or similar)

·       Strong prompt engineering and context engineering (grounding, RAG, memory patterns); MCP/A2A experience

·       Cross-account IAM architecture experience — designing and implementing IAM roles, trust policies, and permission boundaries for multi-agent systems that span AWS accounts

·       API integration experience (consumer/client); IaC using Terraform or CloudFormation

·       AWS Bedrock (Models, Guardrails); Lambda, API Gateway, S3, IAM, KMS, Secrets Manager, ECR, Basic VPC

Should Have

·       Bedrock AgentCore Services; CloudWatch, DynamoDB, EventBridge, Step Functions, ECS Fargate

·       Agent evaluation experience (automated scoring, performance tracking)

·       Inter-agent communication patterns (MCP, A2A) in multi-account environments — cross-account invocation, service control policies (SCPs), and resource-based policies for agent-to-agent access

·       API Security (OAuth2, ApiKey, BasicAuth)

·       Observability (logging, metrics, tracing); CI/CD pipeline setup

·       Vector databases and retrieval patterns

·       GenAI coding assistants (Kiro, Q Developer)

·       Legacy technology familiarity (Java/Spring, Sybase, DB2, or COBOL) as source context for agentic modernization or integration pattern design

·       Financial services or regulated-industry experience (compliance-aware delivery: trade surveillance, data controls, audit requirements)

·       Large-scale portfolio delivery experience — reusable patterns or components applied across 50+ applications, including wave planning and throughput measurement