Senior Software Engineer at Microsoft

Bengaluru, karnataka, India -

Full Time

Start Date

Immediate

Expiry Date

05 Mar, 26

Salary

0.0

Posted On

05 Dec, 25

Experience

10 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

ETL Pipelines, GPU Inference, Performance Tuning, Distributed Systems, Streaming Frameworks, Kubernetes, Containers, Observability Stacks, C++, Java, Python, Kafka, Flink, Spark, OpenTelemetry, Prometheus, Triton

Industry

Software Development

Description

Overview We are looking for a Senior Software Engineer who thrives on hands-on coding and problem solving to build the real-time data pipelines and serving systems that power large-scale ML models. You will be directly responsible for designing, coding, and optimizing ETL pipelines, GPU inference serving that ensure models get the freshest data and serve results with millisecond-level latency. This role is ideal for someone who loves to write high-quality production code, profile and debug performance bottlenecks, and ship optimizations at scale, while collaborating closely with applied scientists and other engineers. Microsoft’s mission is to empower every person and every organization on the planet to achieve more. As employees we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond. Responsibilities Design & code real-time ETL/feature pipelines (e.g., Flink or Spark Structured Streaming) feeding online stores/caches with strict freshness. Define and meet SLOs with OpenTelemetry/Prometheus/Grafana for metrics, tracing, and alerting. Implement robust queuing/streaming with Kafka/Pulsar. Optimized GPU inference services on Triton Inference Server (or ONNX Runtime/TensorRT). Profile & optimize end-to-end: CPU/GPU utilization, memory, I/O, vectorization, caching etc. Ship safely with CI/CD. Collaborate with applied scientists on feature contracts, embedding pipelines, validation. Code reviews, docs, and mentoring. Qualifications Required Qualifications: Bachelor's Degree in Computer Science or related technical field AND 8+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR equivalent experience. 6+ years building distributed systems in production. Production experience with streaming frameworks (Flink or Spark ) and messaging (Kafka). Hands-on with Kubernetes and containers; comfort with service ops (logs, metrics, scaling). Practical experience with GPU inference on Triton or ONNX Runtime/TensorRT (model packaging, runtime tuning, batching). Performance tuning (profilers/flamegraphs), concurrency, networked services. Familiarity with observability stacks (Prometheus, Grafana, OpenTelemetry). Tech stack: ML Sys| Flink | Spark | Kafka | Azure | Kubernetes | Triton | ONNX | OpenTelemetry | Prometheus | Grafana |GPU inference |OpenAI Models Other Requirements: Ability to meet Microsoft, customer and/or government security screening requirements are required for this role. These requirements include but are not limited to the following specialized security screenings: Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud background check upon hire/transfer and every two years thereafter. Preferred Qualifications: Master's Degree in Computer Science or related technical field AND 8+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR Bachelor's Degree in Computer Science or related technical field AND 8+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR equivalent experience. Experience with real-time feature stores or embedding pipelines. Prior contributions to GPU batching, dynamic scheduling, or multi-model serving. 6+ years building distributed systems in production. This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled. Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations and ordinances. If you need assistance with religious accommodations and/or a reasonable accommodation due to a disability during the application process, read more about requesting accommodations.

Responsibilities

Design and code real-time ETL/feature pipelines and implement robust queuing/streaming systems. Collaborate with applied scientists and optimize GPU inference services for large-scale ML models.