SDE II - ML
Glance · Bengaluru · onsite · Posted 30d ago
Undisclosed3–8 yrsfulltimeSourced from
About a minute. You'll make an account on the way through.
About this role
We are looking for an SDE 2, Machine Learning to help build the core systems behind Glances AI shopping agent. In this role, you will work on low-latency ML inference platforms, automated evaluation harnesses, and rapid 0 1 prototyping for new AI shopping features. You will also partner directly with applied scientists and backend engineers to take experimental ML models into reliable production environments.
Responsibilities
- ML Inference Platform: Build and scale systems running recommendation inference, vector search, feature store queries, and real-time data updates.
- Evaluation Harness: Develop automated offline and online evaluation frameworks, regression tests, and latency/cost tracking tools to evaluate model releases.
- Rapid Prototyping: Rapidly prototype and test new engineering ideas for the Glance AI shopping agent, turning promising concepts into scalable platform components.
- System Performance: Optimize throughput and reduce serving latency across CPU and GPU clusters for high-volume ML workloads.
Requirements
- Engineering Foundations: Strong coding skills in Python or Java, with solid background in distributed systems.
- ML Serving Tools: Hands-on experience with model serving tools (Triton, vLLM, TorchServe), vector databases (Qdrant, Faiss), feature stores databases.
- Evaluation Systems: Experience building testing pipelines, regression suites, or shadow deployment setups for ML services.
- Execution Ownership: Comfortable navigating technical ambiguity, moving quickly, and shipping code in fast-paced teams.
Qualifications
- BTech or MTech in Computer Science, Machine Learning, or a related technical field.
- 3+ years of software engineering experience, with 2+ years focused on ML infrastructure, model serving, or recommendation systems.
- Hands-on experience deploying recommendation pipelines, vector search, or feature stores to production.
- Proficiency in Python, system profiling, and query performance tuning.
- Experience setting up model monitoring and maintaining high-throughput production ML systems.
- Ability to collaborate closely with Applied Science teams to turn models into production services.
- Self-directed, curious, and comfortable building solutions from 0 1.
Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.
Sourced from naukri
Skills
PrototypingprofilingModel MonitoringRapid PrototypingPerformance TuningDistributed SystemsregressionPrototypeFAISSgeminiML modelsdeploymentPythonadvertisingJavaArchitecturehyperArtificial IntelligenceMachine LearningML Serving
About Glance
Glance
Internet
281
employees
2019
7 years old
Bangalore / Bengaluru, Karnataka
IN
₹28.1L PA avg
Avg at Glance
About
Glance is a digital platform that personalizes online content for users, enhancing the browsing experience through attractive, language-specific display on lock screens.
Industries
Internet
Employee ratings
10 reviews
3.3/ 5
Culture
3.1
Career growth
2.9
Work-life
3.4
Employees rate it well for
Company Culture35Compensation & Benefits33
Find them on