14 hours ago
Bengaluru, IndiaMid Level
Responsibilities
- Build and scale ML inference systems for recommendation inference, vector search, feature-store queries, and real-time data updates.
- Develop automated offline and online evaluation frameworks, regression suites, shadow deployments, and latency/cost tracking tools.
- Rapidly prototype AI shopping-agent concepts and turn successful ideas into scalable platform components.
- Optimize throughput and serving latency across CPU and GPU clusters for high-volume ML workloads.
- Deploy and maintain high-throughput production ML systems, including monitoring and performance tuning.
- Collaborate with applied scientists and backend engineers to productionize experimental ML models.
Requirements
- Strong coding skills in Python or Java and a solid foundation in distributed systems.
- Hands-on experience with model-serving tools such as Triton, vLLM, or TorchServe; vector databases such as Qdrant or Faiss; and feature stores or databases.
- Experience building testing pipelines, regression suites, or shadow-deployment setups for ML services.
- BTech or MTech in Computer Science, Machine Learning, or a related technical field.
- At least 3 years of software engineering experience, including at least 2 years focused on ML infrastructure, model serving, or recommendation systems.
- Experience deploying recommendation pipelines, vector search, or feature stores to production.
- Proficiency in system profiling and query-performance tuning, plus experience with model monitoring and high-throughput production ML systems.
- Ability to collaborate with Applied Science teams, work through ambiguity, and build solutions from 0 to 1.
Categories
About Glance
Glance builds AI-driven commerce and content platforms that surface personalized shopping and media on mobile lock screens, connected TVs, and apps. Its products include Glance, Roposo, and Nostra, partnering with smartphone and TV manufacturers, telecom providers, and brands to enable discovery-led shopping and entertainment, monetized through advertising and commerce. Founded in 2019 and headquartered in Bangalore, it operates as an unconsolidated subsidiary of InMobi, is backed by Google and Jio Platforms, and runs on 450M+ devices.