Machine Learning Engineer

· Bachelors in computer science, Electrical/Computer Engineering, or a related field required; Master’s preferred (or equivalent industry experience)., · Strong systems/ML engineering with exposure to distributed training and inference optimization., · 3-5 years in ML/AI engineering roles owning training and/or serving in production at scale.

\n

· Demonstrated success delivering high-throughput, low-latency ML services with reliability and cost improvements.

\n

· Experience collaborating across Research, Platform/Infra, Data, and Product functions., · Familiarity with deep learning frameworks: PyTorch (primary), TensorFlow.

· Productize and optimize models from Research into reliable, performant, and cost-efficient services with clear SLOs (latency, availability, cost).

\n

· Scale training across nodes/GPUs (DDP/FSDP/ZeRO, pipeline/tensor parallelism) and own throughput/time-to-train using profiling and optimization.

\n

· Implement model-efficiency techniques (quantization, distillation, pruning, KV-cache, Flash Attention) for training and inference without materially degrading quality.

\n

· Build and maintain model-serving systems (vLLM/Triton/TGI/ONNX/TensorRT/AITemplate) with batching, streaming, caching, and memory management.

\n

· Integrate with vector/feature stores and data pipelines (FAISS/Milvus/Pinecone/pgvector; Parquet/Delta) as needed for production.

\n

· Define and track performance and cost KPIs; run continuous improvement loops and capacity planning.

\n

· Partner with ML Ops on CI/CD, telemetry/observability, model registries; partner with Scientists on reproducible handoffs and evaluations.

\n

\n, · Exposure to large model training techniques (DDP, FSDP, ZeRO, pipeline/tensor parallelism); distributed training experience a plus

\n

· Optimization: experience profiling and optimizing code execution and model inference: (PTQ/QAT/AWQ/GPTQ), pruning, distillation, KV-cache optimization, Flash Attention

\n

· Scalable serving: autoscaling, load balancing, streaming, batching, caching; collaboration with platform engineers.

\n

· Data & storage: SQL/NoSQL, vector stores (FAISS/Milvus/Pinecone/pgvector), Parquet/Delta, object stores.

\n

· Write performant, maintainable code

\n

· Understanding of the full ML lifecycle: data collection, model training, deployment, inference, optimization, and evaluation.

\n

Welcome to ConsultNet, a premier national provider of technology talent and solutions. Our expertise spans across project services, contract-to-hire, direct search, and managed services onshore, nearshore, and hybrid. For over 25 years, we have connected thousands of consultants with meaningful roles through a personal, communication-driven approach, partnering with a diverse client base to build high-performing teams and create lasting impact. Our comprehensive service offerings cover a wide range of technology and engineering positions across key markets nationwide. Learn more at www.consultnet.com .