Posted 5 days ago
GenAI DevOps Engineer / AI Engineer
@ Accion Labs
Canada
Overview
Accion Labs is hiring a contract GenAI DevOps and AI Engineer for LLMOps work on AWS AgentCore. The role builds and operates agent runtime environments, CI/CD and evaluation pipelines for LLM agents, with requirements around GitHub Actions, Terraform, Python and LLM evaluation.
Responsibilities:
- Set up and operate AgentCore runtime environments
- Build CI/CD pipelines with GitHub Actions and Terraform
- Design evaluation pipelines and LLM-as-judge systems
- Integrate evaluations as CI gates
Requirements summary:
- Hands-on AgentCore runtime deployment and VPC mode experience
- Strong AWS, IAM and container image skills
- Python proficiency
- Experience with golden datasets and LLM evaluation
Tools & skills
Source and dates
Source type not verified · apify-linkedin
- Employer posting date
- 2026-11-05
- First seen by our source
- 2026-11-10
- Source record updated
- 2026-11-10
These dates describe the source record, not a live verification that the employer is still hiring. Check the original posting.
Job details
| Department | Software development |
| Work setting | Office, Home |
| Position | Mostly sitting |
| Physical demands | physical low · computer high |
| Languages | English |
Summary and details written by AI from the posting; the employer’s posting is the authority.
Accion Labs
| Field | Value |
|---|---|
| Open jobs on Jobsy | 2 |
On LLMOp/DevOps they are looking for people who have setup and operated the Agentcore runtime environment.
DevOps
MUST
- AI-DLC practices
- Agentic code generation (Claude Code SDK, Kiro CLI) with human-in-the-loop checkpoints
- GitHub Actions: reusable workflows, environments and approvals, OIDC federation to AWS
- Container image builds and Amazon ECR (AgentCore Runtime requires ARM64 images)
- AgentCore Runtime deployment (versions, endpoints, rollback) and VPC mode
- VPC endpoints / PrivateLink and security groups
- Event-driven automation: EventBridge, Lambda, Step Functions
- Terraform
- IAM for CI/CD
SHOULD
- AgentCore Gateway rate limits and PortKey admin API (kill switch)
- Game-day practice with audit evidence
- Image signing (Cosign)
- Python
COULD
- Strands Agents SDK
- Backstage templates
- ROSA / OpenShift networking (later phase)
- AI eng
MUST
- AgentCore Evaluations and Bedrock evaluation
- Golden-dataset design and curation with SMEs
- LLM-as-judge design and calibration against human labels
- Integrating evaluations as a CI gate
- Langfuse / OpenTelemetry
- Python
SHOULD
- RAGAS or equivalent
- Trajectory evaluation
- Understanding of agentic red-teaming results (to feed them into the gate)
COULD
- Bedrock Guardrails
- Sampling design for continuous evaluation
- Strands Agents SDK
Journal
Only you can see this. Kept on this device, and in your account when you sign in.