Quick Overview
Job Description
Senior Platform Engineer – AI Gateway, Identity & Observability
Location: Oaks, PA
Type: Long-Term Contract
Experience: 10+ Years
Work Model: Hybrid – Onsite from Day 1
Seeking a Senior Platform Engineer with 10+ years of experience, including 5+ years in API platforms, Identity, or Observability, to build and operate an enterprise AI platform supporting secure, reliable, and observable AI/LLM workloads.
Key Responsibilities
- Design and implement an AI Gateway for routing model traffic across Azure/cloud, third-party, and on-prem environments.
- Implement routing, rate limiting, quotas, authentication, retries, failover, circuit breaking, caching, and request/response transformation.
- Build agent identity and registration using secure workload/service identities.
- Lead production hardening and migration of existing API services to the long-term gateway.
- Establish LLM observability, distributed tracing, monitoring, and reliability standards.
- Support production operations, incident response, capacity planning, and platform optimization.
Required Skills
- 5+ years in API Platform, Identity, or Observability engineering.
- 4+ years API Gateway experience; Azure API Management preferred. Apigee/Kong also acceptable.
- Strong OAuth2, OpenID Connect, JWT, Managed Identity, Service Principals, and Secrets Management.
- OpenTelemetry and distributed tracing experience.
- Strong SRE/Production Engineering experience including SLOs, alerting, incident response, and reliability.
- 2+ years LLM/AI production experience, including model routing, token limits/quotas, streaming, and content filtering.
- Experience with Langfuse, LangSmith, Arize, or similar AI observability platforms.
- Experience with Docker/Kubernetes, cloud infrastructure, networking, TLS/certificates, DNS, and IaC.
- Programming experience in Python, C#, or equivalent.
Tekshapers is an equal opportunity employer and will consider all applications without regards to race, sex, age, color, religion, national origin, veteran status, disability, sexual orientation, gender identity, genetic information or any characteristic protected by law.
Similar jobs
- WA
Incident management / reliability / SRE Evaluator
NewWeekday AI
United States🇺🇸Remote20 hours agoGoogle WorkspaceMicrosoft OfficeTechnology - C-
Contract Site Reliability Engineer II
NewC-Serv
Arlington, Virginia🇺🇸$60 - $90/hrHybrid17 hours agoAWSLoad BalancingArgoCD+8Technology - C-
Contract Site Reliability Engineer II
NewC-Serv
Reston, Virginia🇺🇸$60 - $90/hrHybrid17 hours agoAWSLoad BalancingArgoCD+8Technology - C-
Contract Site Reliability Engineer II
NewC-Serv
San Jose, California🇺🇸$60 - $90/hrHybrid17 hours agoAWSLoad BalancingArgoCD+8Technology - C-
Contract Site Reliability Engineer II
NewC-Serv
San Francisco, California🇺🇸$60 - $90/hrHybrid17 hours agoAWSLoad BalancingArgoCD+8Technology - SO
AWS DevOps Engineer
NewSystem One
Lafayette, LA🇺🇸HybridYesterdayAWSGitLab CIJenkins+1Technology