Machine Learning Engineer

Hi,

Good day!

If you are intrested with the below job role then please reply with updated resume and Contact details.

Role: ML Engineer

Hybrid: 3 Days onsite – NYC, NY

Type: Contract

Duration: Long Term

Candidates whose primary background is MLOps platform work (DAG orchestration, Terraform, Kubernetes administration, generic CI/CD pipelines) will not be a fit. We need a senior level engineer who can profile a transformer, rewrite its serving path for a 2–3x latency reduction, tune an HNSW index, and tell us which SageMaker instance type will hit our p95 target at the lowest cost.

Roles & Responsibilities

• Design, build, and scale ML-powered inference systems that process large volumes of text, image, and video data to power news-based intelligence products.
• Productionize and optimize state-of-the-art models and inference pipelines. These models include, but are not limited to:
• DistilBERT for Named Entity Recognition (NER) over hundreds of thousands of search queries/day
• TransNetV2 for video shot boundary detection at scale for archival video as well as real-time
• SBERT for embedding generation from textual descriptions
• External multimodal APIs for image/video captioning
• Support hybrid search architectures by defining embedding/re-ranking interfaces, evaluation metrics, and inference performance requirements; partner with search/platform engineers on index configuration, sharding, and cluster tuning.
• Design and implement scalable data processing pipelines across hybrid CPU/GPU environments to handle millions of media assets.
• Partner with MLOps and platform engineering to enable the deployment and operation of ML systems reliably, contributing to:
• Distributed inference architectures
• Cloud-based execution (e.g., AWS EC2, Batch, Lambda, SageMaker)
• Efficient resource utilization across workloads
• Optimize inference latency and throughput across distributed workloads using cloud-based resources (AWS EC2, Batch, Lambda, SageMaker, etc.)
• Build resilient asynchronous processing systems for large-scale workloads, ensuring:
• Reliability (retries, fault tolerance)
• Efficiency (caching, deduplication)
• Observability (metrics, logging, traceability)
• Work closely with data scientists and product teams to iterate on models, improve performance, and deliver measurable impact in production.

Requirements:

• 8+ years of experience building ML inference systems.
• Demonstrated ownership of deep-learning inference optimization in production (quantization, distillation, compilation, kernel/profile-level performance work) for transformer NLP and/or CV models.
• Experience with TensorFlow (SavedModel, tf.data, XLA, TFLite) & PyTorch (TorchScript, ONNX, FastAPI/TorchServe)
• Hands-on experience optimizing inference pipelines on AWS infrastructure, across different types of media assets.
• Experience with video frameworks/tools (e.g., FFmpeg) and working with large-scale frame-level inference.
• Demonstrated experience monitoring and debugging model latency, memory, and pipeline throughput.
• Experience with hybrid search architectures (BM25 + vector search + cross-encoder reranking).
• Familiarity with OpenAI APIs or other foundation model providers.
• Familiarity with open source HuggingFace LLMs.
• Experience with data pipeline and workflow orchestration tools (e.g., Airflow)