Role Overview

We are looking for an engineer to bridge the gap between ML research and production systems. You will integrate, optimize, and operationalize machine learning components within a larger agentic analytics platform.

You will not be responsible for inventing algorithms, but for making them fast, scalable, and production-ready.

Key Responsibilities

• Integrate ML algorithms into production pipelines and APIs
• Optimize model execution (latency, throughput, memory usage)
• Build and maintain model serving infrastructure
• Collaborate with algorithm developers to productionize algorithms
• Develop testing and validation frameworks for ML components
• Implement caching and provenance mechanisms for models code and dataset trails
• Contribute to CI/CD pipelines for model deployment
• Implement regression testing facility for monitoring the analytics engine performance

Required Skills

• Strong Python experience in ML ecosystems (3+ years)
• Experience deploying models in production environments
• Knowledge of model serving patterns (APIs, batch, streaming)
• Familiarity with performance optimization and profiling
• Understanding of ML lifecycle and MLOps practices
• Experience integrating ML systems with backend APIs

Nice to Have

• Experience with ML tooling (MLflow, Kubeflow, DVC)
• Familiarity with java and vector databases / embeddings systems
• Experience with real-time inference systems
• Knowledge of parallel/distributed computing

What Success Looks Like

• ML algorithms run efficiently and reliably in production
• Seamless integration between ML, backend, and agent layers
• Scalable inference pipelines with low latency
• Strong observability of model behavior and performance