Staff Software Engineer - Platform & Reliability

The S r. S t aff Sof t ware Engineer

• Pla t form & Reliabili t y will be p art of t he new Produc t Engineering t eam t asked wi t h designing and building t he nex t genera t ion of Agen t ic A I
• powe r ed p r od u c t s fo r . Ac tin g a s th e Tec hni c al Lead an d Primary A r c hit ec t, yo u w ill be a han ds-o n l e a de r r espo n s i b l e fo r th e t e am s ove rall de li ve r y of th e runtim e e n v ir o nm e nt an d aut o mati o n fo r A I se r v i ces an d Age nt s . Yo u w ill lead a s mall sq ua d by deco m pos in g co m p l ex p lat fo rm r eq uir e m e nt s-s u c h a s A I
• spec i f i c C I / C D, a ge nt obse r v a b ilit y , an d aut o mat ed sc alin g
• int o a c ti o na b l e ta sks w hil e r e mainin g deep l y e m bedded in th e codeb a se K ey R esp o ns i b iliti es
• T echn i ca l Lead & E xecu tio n: Lead t he t echnical delivery of t he Agen t ic Pla t form by t ransla t ing high-level infras t ruc t ure roadmaps in t o ac t ionable developmen t t asks . Yo u w ill ow n ta sks b r e a kdow n fo r yo ur sq ua d , e n s urin g hi g h
• q ualit y o ut p ut thr o u g h t ec hni c al m e nt o r s hi p an d ri go r o u s ar c hit ec tural ove r s i g ht.
• A u t o m a t ed A gen t D elive r y

• C I /C D

  Archi t ec t and implemen t high-veloci t y C I/ CD pipelines specifically designed for t he lifecycle of A I Agen t s and services , including au t oma t ed model evalua t ion and blue-green deploymen t s for agen t ic workflows on Google Cloud Platform .
• Cl oud I nf r as tr uc t u r e E ng i nee ri ng: Lead t he design and implemen t a t ion of our cloud-na t ive infras t ruc t ure on Google Cloud Platform using Terraform and Kuberne t es ( GKE ) . You will own t he core run t ime environmen t where au t onomous agen t s and t ransac t ional microservices coexis t.
• A gen ti c O bse r vab ilit y &

S RE :

Apply SRE principles t o build a specialized moni t oring and aler t ing s t ack for A I agen t s . You will implemen t t racing for agen t "reasoning loops" and ensure t he reliabili t y of t he underlying Vec t or and Graph da t a s t ores .

• AI•N a ti ve S DLC L eade r sh i p: Ac t ively u t ilize coding agen t s t o plan , genera t e , and refac t or pla t form code and I nfras t ruc t ure as Code I aC , main t aining high veloci t y while ensuring code quali t y .

• Sca le & Per f orm a n c e : Mo nit o r an d op timi ze th e pe r fo rman ce an d cos t
• effec ti ve n ess of A I wo r k l o a ds , e n s urin g o ur p lat fo rm can han d l e hi g h
• f r eq u e n cy a ge nt c all s an d multi
• m od al d ata p r ocess in g .
• Secu rit y & Go ve r nance: Own t he implemen t a t ion of secure run t ime boundaries , ensuring t ha t bo t h human users and A I agen t s opera t e wi t hin s t ric t, audi t ed permission se t s

Experience:

10+ years of Software or Platform Engineering experience, with a background as a hands-on engineer who has successfully led technical squads.

Technical Stack:

Expert mastery of Google Cloud Platform (GKE, Vertex AI), Terraform, Kubernetes, and Python.

Product AI Platform:

Proven track record of designing and shipping production platforms for AI/LLM workloads, including specialized CI/CD and observability for agentic architectures.

Reliability Mindset:

Strong command of SRE principles, including experience with SLOs, error budgets, and troubleshooting complex distributed systems.

Cloud Infrastructure:

Experienced in working with cloud platforms (Google Cloud Platform, AWS) and deploying containerized services that are secure and scalable.

Coding Agents:

Demonstrated proficiency in using coding agents to accelerate the SDLC and plan and code complex engineering tasks.