Ai Ml Engineer

Juuuno Inc.; Sector 10; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

Juuuno Inc. in India seeks an AI/ML engineer to design and build LLM workflows with structured outputs, routing, retrieval and control.

You will create data pipelines, feature workflows, training datasets and model registries while ensuring reproducible experiments. You will monitor model quality, implement safeguards, and deploy AI capabilities as versioned APIs, collaborating with backend, frontend, QA and security teams.

Qualifications

• 3–7 years in applied AI/ML with production models
• Strong Python skills and ML framework experience
• Experience deploying LLM-based systems and API integrations
• Solid understanding of precision/recall/calibration, drift, and error analysis

Responsibilities

• Design and build LLM workflows using structured outputs, tool calling, routing, retrieval (RAG) and controlled orchestration
• Build predictive models for classification, ranking, forecasting, anomaly detection and recommendation
• Create data pipelines, feature workflows, training/evaluation datasets, model registries and reproducible experiments
• Define offline/online evaluation, regression suites, quality thresholds and human-review processes
• Monitor model quality, drift, latency, usage and cost; diagnose and fix failures using measured feedback
• Implement safeguards against prompt injection, unsafe tool use, data leakage and unsupported model claims
• Deploy AI capabilities as versioned, documented APIs and work closely with backend, frontend, QA and security teams
• Build reusable AI foundations that serve multiple products

Skills

Python

scikit-learn

PyTorch

TensorFlow

LLM APIs

prompt engineering

structured outputs

SQL & time-series

model monitoring

communication

Tools

LangGraph

Job description

Role & responsibilities

• Design and build LLM workflows using structured outputs, tool/function calling, routing, retrieval (RAG) and controlled orchestration
• Build predictive models for classification, ranking, forecasting, anomaly detection and recommendation
• Create data pipelines, feature workflows, training/evaluation datasets, model registries and reproducible experiments
• Define offline/online evaluation, regression suites, quality thresholds and human-review processes
• Monitor model quality, drift, latency, usage and cost; diagnose and fix failures using measured feedback
• Implement safeguards against prompt injection, unsafe tool use, data leakage and unsupported model claims
• Deploy AI capabilities as versioned, documented APIs and work closely with backend, frontend, QA and security teams
• Build reusable AI foundations that serve multiple products

Preferred candidate profile

• 3 - 7 years in applied AI/ML, with production models or LLM-enabled systems
• Strong Python; hands-on with scikit-learn, PyTorch, TensorFlow or equivalent
• Production experience with LLM APIs, structured outputs, function calling, retrieval and prompt evaluation
• Solid grasp of precision, recall, calibration, drift, experiment design and error analysis
• Comfortable with SQL, event data, time-series and large analytical datasets
• Experience deploying models behind APIs with versioning and monitoring
• Good judgement on when to use rules, classical ML, LLMs or a hybrid
• Clear communicator with technical and non-technical stakeholders

Good to have

• LangGraph or similar orchestration frameworks
• Time-series forecasting, causal inference, uplift modeling, recommendations or contextual bandits
• Multimodal (image, audio, video) analysis
• AI observability/evaluation platforms, inference optimization, LLM cost management
• Experience building shared AI platforms for multiple product teams

Why Join Us

• Core technology role owning AI from build to production across multiple digital products
• Move beyond demos: ship real, measurable, production-grade AI
• Shape reusable AI foundations and future product versions
• Work across LLM systems and predictive ML with a strong engineering team