5 months ago
Bengaluru, IndiaEntry Level
Responsibilities
- Build operational dashboards using LLM APIs and visualization tools, integrating AI-generated insights and automated retail KPI metrics.
- Develop prompt pipelines, RAG workflows, and autonomous AI agents for escalation triage, store operations, maintenance, workforce optimization, and new store openings.
- Define agent architectures, tool integrations, memory strategies, escalation rules, reliability controls, and auditability standards.
- Monitor and improve deployed AI/ML models using accuracy, recall, F1, business KPIs, feedback loops, fine-tuning, prompt engineering, A/B testing, and validation data.
- Build and maintain ETL/ELT pipelines ingesting data from POS, ERP, IoT, ticketing, and SaaS systems.
- Design analytical and ML data schemas while ensuring data quality, lineage, governance, and documentation.
- Translate retail business problems into ML/AI use cases and support adoption by non-technical retail staff.
- Collaborate with retail operations, maintenance, new store opening teams, senior leadership, and other non-technical stakeholders.
Requirements
- 1–3 years of professional experience in data engineering, ML engineering, or a related AI/software role.
- Proficiency in Python, including pandas, NumPy, scikit-learn, and FastAPI or Flask.
- Experience with LLM APIs such as Anthropic Claude, OpenAI GPT, Google Gemini, or Mistral.
- Knowledge of prompt engineering, RAG pipelines, and agent frameworks such as LangChain, LangGraph, or CrewAI.
- SQL experience and working knowledge of Snowflake, BigQuery, or Redshift.
- Experience with dbt, Airflow, Prefect, or equivalent data pipeline tools.
- Familiarity with Pinecone, Weaviate, or ChromaDB for vector-based RAG architectures.
- Dashboard or visualization experience with Streamlit, Tableau, Power BI, Metabase, or similar tools.
- Experience with Git, CI/CD pipelines, and basic ML model training, evaluation, deployment, and monitoring.
- Strong communication, problem-solving, cross-functional collaboration, adaptability, attention to detail, and commitment to responsible AI practices.
- SaaS company experience, retail or supply-chain exposure, multimodal AI, agentic tool-use patterns, retail systems, Kafka or Kinesis, internal operations tooling, and responsible AI or model governance experience are preferred or nice to have.
Benefits
- Hybrid work arrangement with on-site and remote work.
- Full-time junior-level position.
- Mentorship from experienced data and ML engineers with a fast-track growth path.
- Hands-on work with LLM APIs and agentic AI architectures from day one.
- Direct impact on operations serving thousands of stores and millions of customers.
- Collaborative SaaS-style product culture in a retail-technology environment.
Tech Stack
Amazon RedshiftApache AirflowApache KafkadbtFastAPIFlaskGitGoogle BigQueryMetabaseNumPyPandasPythonReactscikit-learnSnowflakeSQL
Categories
