EngineeringFull-time
Python AI/ML Engineer
Remote
Full-time
₹12-36 LPA
100% Remote
Job Description
Join Noveum's core AI team that monitors, evaluates, and improves AI agents in production. You will design rigorous eval pipelines, build and debug agentic workflows, deploy and tune models, and close the loop with observability to drive reliability, quality, and cost/performance. This is a high-ownership role working directly with founders and customers to ship end-to-end fixes and new agent capabilities.
Key Responsibilities
- Design and implement production-grade AI agent architectures and tools
- Build rigorous evaluation pipelines; define metrics, datasets, and pass/fail thresholds
- Instrument, monitor, and debug agents using tracing/observability to improve reliability
- Deploy, fine-tune, and optimize models (latency, cost, and accuracy)
- Collaborate with founders and customers to scope, build, and ship new agent capabilities
- Mentor and raise the bar on engineering quality and operational excellence
Requirements
- 5+ years in AI/ML engineering with hands-on model development and deployment
- Expertise in Python with PyTorch and/or TensorFlow
- Production experience with LLMs/GenAI (OpenAI, Anthropic, etc.)
- Proven experience building agentic systems or complex ML pipelines
- Strong MLOps foundations: packaging, CI/CD, containers, cloud
- Bias for ownership: able to self-unblock, deliver end-to-end, and operate independently
Preferred Qualifications
- Hands-on experience designing/running evals for LLMs/agents
- Experience building new agents and tools for real customer workflows
- Open-source contributions or public work in AI/ML
- Next.js familiarity is a plus but not required