Machine Learning Engineer
Job Description
Experience: 4-8 Years
Location: Pune, Baner (Hybrid)
Shift: Open to 24×7 Weekly Rotational Shifts
Must-Have Skills
- LLM Inference: vLLM, TGI, TensorRT-LLM, SGLang, KV Cache.
- RAG & Agentic AI: RAG, LangGraph/LlamaIndex, embeddings, tool calling.
- ML Engineering: Python, PyTorch, Hugging Face, LoRA/QLoRA, quantization.
- AI Infrastructure: GPU, Docker, Kubernetes, Linux.
- Observability: LangSmith, Langfuse, W&B, Prometheus, Grafana.
- Shift: Willingness to work in 24×7 rotational shifts.
More Info
Job Type:
Industry:
Employment Type:
Key Skills
embeddings
ML Engineering
tool calling
Hugging Face
LLM Inference
SGLang
LangSmith
Langfuse
RAG LangGraph
quantization
Observability
TensorRT-LLM
KV Cache
vLLM
Agentic AI
TGI
LoRA
RAG
W B
LlamaIndex
QLoRA
AI Infrastructure
About Company
Skills:
Deep Learning, Git, Computer Vision, Python, real-time video streams, model optimization techniques, data preparation or processing pipelines, large-scale image and video datasets
Skills:
Machine Learning, Tensorflow, Pytorch, Docker, automation, Python, AWS, Git, MLops, Gcp, Azure, Kubernetes, Airflow, Infrastructure as Code, model versioning, MLflow, Kubeflow, model registries, feature stores, DevOps practices, Scikit-learn, Ai, Monitoring, CI CD pipelines, ML model deployment
Skills:
Docker, Pyspark, Pytest, Azure Databricks, Azure Cloud Services, Python, Sql, MLflow
Skills:
Java, Machine Learning, Distributed Systems, Hadoop, Statistical Modelling, Sql, API Design, MLops, Spark, Python, Scalable Architectures, Large-scale Data Systems, Go, Optimisation Techniques, Scientific Computing
Skills:
Spark, Java, Hadoop, Cloudformation, Yarn, Tensorflow, Hive, MLops, Docker, Sns, Python, Kubernetes, AWS, Airflow, Pipelines, H2O, EventBridge, CodeBuild, SageMaker, CodePipeline, CodeCommit, CloudTrail