- Company Name
- Cresta
- Job Title
- Senior Software Engineer, Backend (AI Platform)
- Job Description
-
**Job Title**
Senior Software Engineer, Backend (AI Platform)
**Role Summary**
Lead the design, development, and maintenance of high‑performance backend systems that serve AI models and support ML pipelines for a large‑scale AI platform. Drive end‑to‑end automation of data preparation, training, evaluation, and deployment across Kubernetes environments while ensuring reliability, observability, and cost efficiency.
**Expectations**
- Deliver production‑ready code with rigorous testing, code review, and continuous delivery practices.
- Mentor junior engineers on ML best practices, observability, and incident response.
- Collaborate cross‑functionally with research, product, and operations teams to enable rapid, safe model deployment.
**Key Responsibilities**
- Own low‑latency, highly available model serving stacks for in‑house ML and partner LLM frameworks.
- Orchestrate data pipelines, training workflows, and model registry updates on Kubernetes, applying solid MLOps principles.
- Profile, tune, and scale throughput, memory, and cost using caching, sharding, batching, and GPU/CPU autoscaling.
- Build reusable SDKs, templates, and CLI tools that abstract platform primitives for research and product teams.
- Implement deep observability (tracing, metrics, alerts) and conduct blameless post‑mortems.
**Required Skills**
- 5+ years of production software engineering with at least 2 years in ML platform or infrastructure.
- Advanced Python (async, typing, packaging, performance).
- Working knowledge of Golang for systems components.
- Hands‑on experience with serving frameworks such as vLLM, Triton, or TorchServe.
- Expertise in Kubernetes and cloud‑native operations.
- Strong understanding of distributed systems, networking, and container security.
- Proficiency in rigorous testing, code review, and CI/CD pipelines.
**Nice‑to‑have**
- Experience with large language models or real‑time streaming inference.
- IaC tooling: Terraform, Helm, or similar.
- Background in speech or conversational AI domains.
**Required Education & Certifications**
- Bachelor’s degree in Computer Science, Software Engineering, or a related technical field.
---