Job Description
Roles & Responsibilities:
As an AI Engineer in Data Intelligence Unit, you will help build and operate the core building blocks of Data Representation learning and Context Engineering across the credit Risk, Fraud/FRM, Sales, Collections & Recovery. You will work with senior engineers and Data scientists to converts raw structured and unstructured data into reliable features, embeddings, retrieval-ready knowledge assets, and repeatable evaluation pipelines – so downstream AI pods can ship models faster, safer, and with measurable quality.
1) Data Representation Pipelines
· Prepare and validate datasets from multiple sources (transactions, bureau, device/digital, documents,
CRM/operations)
· Implement features engineering pipelines (aggregations, ratios, behavior signals) and maintain feature
definitions.
· Build large-scale ML systems: distributed training pipelines, feature stores, model registry, CI/CD for ML, and
scalable batch + near-real-time scoring services.
· Support embedding workflows (text/customer/device/dealer/geo) including batch refresh, versioning, and
lineage.
2) Knowledge Engineering Support (Canonical Objects & Metadata Assets)
· Help create/maintain canonical objects, entity dictionaries, taxonomies/ontologies, and labeling guidelines.
· Support annotation/labeling workflows (quality checks, consistency, sampling) for training and evaluation.
3) Experimentation & Model Operations
· Execute training/inference jobs using established frameworks, log experiments and outcomes.
· Perform error analysis, data leakage checks, and basic model monitoring (drift signals, data anomalies)
· Contribute to deployment readiness: tests, reproducible configs, and incident triage support.
4) Retrieval & Context Engineering Support (LLM/RAG enablement)
· Assist document processing: chunking, cleaning, metadata tagging, indexing access filters.
· Maintain prompt/context templates, grounding rules, and evaluation sets for RAG/LLM assistants used by
Pods.
· Run offline evaluations (retrieval quality, answer quality, regressions) and track metrics across releases.
5) Engineering Hygiene & Governance
· Write clean, testable code; follow Git workflows and CI checks.
· Maintain documentation: dataset cards, feature notes, pipeline SOPs, and release checklists.
· Follow security/privacy controls for regulated data, ensuring traceability and auditability.
______________________________________________________________
Basic Qualifications:
· Bachelor’s/Master’s in CS/Math/Engineering
· 3 to 5 years’ experience in Data Science /Applied ML/ ML Engineering with proven leadership delivering
production – grade ML system at scale.
______________________________________________________________
Required Skills & Competencies Core (must-have)
· Programming: Python (strong), SQL (strong); Git; basic unit testing.
· Data: Pandas/PySpark basics, joins/aggregations/window functions, data validation and profiling.
· ML Fundamentals: supervised/unsupervised learning, embeddings, train/val/test discipline, metrics, and error analysis.
· Applied System Mindset: reproducibility, structured debugging, logging/monitoring fundamentals.
If interested, please share your resume at nikita.tiwari@sattvahuman.com & pooja.chauhan@sattvahuman.com
