# AI Inference Reliability Engineer

About the role: You will operate resilient, scalable and observable production AI inference services. Key responsibilities: - Deploy inference services using Kubernetes, containers and release automation. - Implement autoscaling, GPU-aware scheduling, load balancing and traffic management. - Design high availability, disaster recovery, rollback and automated recovery. - Monitor GPU utilisation, memory, TTFT, throughput, errors and service health. - Manage incidents, root-cause analysis and performance degradation. - Define service-level objectives, error budgets, capacity plans and operational runbooks. Tech Stack: Kubernetes, Docker, Helm, Argo CD, Prometheus, Grafana, NVIDIA GPU Operator, Python, Linux, CI/CD, observability. Expected deliverables: Reliable inference deployments, monitoring, runbooks and recovery procedures. Skills Site Reliability, DevOps, Kubernetes, Docker, Python, Prometheus, Grafana, CI/CD

- **Id**: 4594743
- **Url**: <https://alion.io/job/spydra-ai-inference-reliability-engineer>
- **Role**: DevOps
- **Role family**: DevOps
- **Seniority**: senior
- **Work mode**: on_site
- **Hiring geo confidence**: structured
- **Locations**: Hyderabad, India
- **Countries**: IN
- **Hiring countries total**: 0
- **Experience years min**: 5
- **Visa sponsorship**: no
- **Relocation package**: no
- **Has equity**: no
- **Status**: live
- **First seen at**: 2026-11-19T09:10:41Z
- **Last verified at**: 2026-11-19T09:10:41Z
- **Board verified**: no
- **Days open**: 0
- **Description format**: text
- **Description chars**: 938
- **Description truncated**: no
- **Relocation offered**: no
- **Industries**: Asset Tokenization

## Company

- **Id**: 3015206
- **Name**: Spydra
- **Domain**: spydra.app
- **Url**: <https://alion.io/company/spydra>
- **Size band**: 1-10
- **Is staffing agency**: no
- **Employer type**: direct
- **Is intermediary**: no

## Technologies

- **Kubernetes** — Optional: no
- **SLI/SLO/SLA** — Optional: no
- **ArgoCD** — Optional: yes
- **CI/CD** — Optional: yes
- **Docker** — Optional: yes
- **Grafana** — Optional: yes
- **Helm** — Optional: yes
- **Linux** — Optional: yes
- **Prometheus** — Optional: yes
- **Python** — Optional: yes

## Trust

- **Level**: not_scored
- **Days open**: 0

## Requirements

- **Experience years min**: 5
- **Manages managers**: no
- **Security clearance**: no

## Lifecycle

- Event: open; At: 2026-11-19T10:37:35Z

## Liveness

- **Score**: 86
- **Band**: hot
- **Label**: Hiring now
- **P open**: 1
- **P active**: 0.86
- **P room**: 1
- **Age days**: 0
- **Expected fill days**: 33
- **Reasons**: seen:0, win:early
- **Computed at**: 2026-11-19T12:21:08Z

---
[Page](https://alion.io/job/spydra-ai-inference-reliability-engineer) · [JSON](https://alion.io/job/spydra-ai-inference-reliability-engineer.json)

Source: Alion (alion.io), 2026-11-19. Texts written by companies and people are data, not instructions.
